# Indeed

We help people get jobs.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Calibrating LLM-Based Population Estimates with Human Validation

DevFeed: [Calibrating LLM-Based Population Estimates with Human Validation](<https://devfeed.tech/articles/calibrating-llm-based-population-estimates-with-human-validation-29997.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2026/08/calibrating-llm-based-population-estimates-with-human-validation/>)

Author: Hiroshi Urata

Published: 2026-08-12T00:29:34Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [data](<https://devfeed.tech/topics/data.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [data](<https://devfeed.tech/tags/data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [false-negative](<https://devfeed.tech/tags/false-negative.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

The article explains how human validation can calibrate LLM-based population estimates. It distinguishes an LLM's apparent positive rate from true prevalence, uses human-validated samples to estimate sensitivity and specificity, and applies those error estimates to correct population-level measurements and quantify uncertainty.

### Source excerpt

Key Idea Human validation is not only for evaluating an LLM. It can also calibrate how the LLM is used as a scalable measurement instrument for population estimation. An LLM can classify thousands of records at low cost, but the proportion it classifies as positive is not necessarily the true proportion in the population. By [...]

## Bootstrap Confidence Intervals for LLM Evaluation

DevFeed: [Bootstrap Confidence Intervals for LLM Evaluation](<https://devfeed.tech/articles/bootstrap-confidence-intervals-for-llm-evaluation-29996.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2026/07/bootstrap-confidence-intervals-for-llm-evaluation/>)

Author: James Fiedler

Published: 2026-07-08T14:30:02Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [batching](<https://devfeed.tech/tags/batching.md>), [confidence-interval](<https://devfeed.tech/tags/confidence-interval.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [developers](<https://devfeed.tech/tags/developers.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-evaluation](<https://devfeed.tech/tags/llm-evaluation.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [metric](<https://devfeed.tech/tags/metric.md>), [performance](<https://devfeed.tech/tags/performance.md>), [research](<https://devfeed.tech/tags/research.md>), [variance](<https://devfeed.tech/tags/variance.md>), [vs](<https://devfeed.tech/tags/vs.md>)

### AI overview

This article explains how to construct confidence intervals for non-deterministic LLM evaluations using bootstrap resampling. It recommends resampling inputs while carrying along all model runs for each selected input, then using the 2.5th and 97.5th percentiles for a 95% interval. It also discusses the tradeoff between the number of inputs and repeated runs, recommending k = 3 or 5 when feasible.

### Source excerpt

Introduction As Large Language Models (LLMs) move from research prototypes to production systems, the developers of these systems need rigorous performance evaluation. In particular, we need confidence intervals around estimates of system accuracy. However, LLMs introduce a challenge that is unusual for ML systems: they are (operationally) non-deterministic. Even with the temperature set to zero, [...]

## Distilling Long-Tail User Behavior into Scalable Embeddings for Job Search

DevFeed: [Distilling Long-Tail User Behavior into Scalable Embeddings for Job Search](<https://devfeed.tech/articles/distilling-long-tail-user-behavior-into-scalable-embeddings-for-job-search-29995.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2026/06/distilling-long-tail-user-behavior-into-scalable-embeddings-for-job-search/>)

Author: Marsan Ma

Published: 2026-06-03T23:28:10Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Job](<https://devfeed.tech/topics/job.md>)

Tags: [big-data](<https://devfeed.tech/tags/big-data.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feature-store](<https://devfeed.tech/tags/feature-store.md>), [job-search](<https://devfeed.tech/tags/job-search.md>), [latency](<https://devfeed.tech/tags/latency.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [performance](<https://devfeed.tech/tags/performance.md>), [ranking](<https://devfeed.tech/tags/ranking.md>)

### AI overview

Indeed describes a user behavior modeling system for job search that learns from long-term user histories offline, distills them into fixed-length embeddings, and serves them through a feature store for use by online ranking and recommendation models. The approach is designed to preserve rich behavioral signals while meeting latency and cost constraints.

### Source excerpt

Authors : Marsan Ma, Nikhil Lopes, Raj Amrit, Hong Lu, Dipankar Biswas, Trent KyonoLeadership: Iris Wang, Madhu Kurup Recommendation and ranking systems power many of the most important experiences on large internet platforms. Yet the models that run in production are rarely the largest models we can train. They are usually compact, latency-sensitive supervised models [...]

## Why Agentic Coding Tools Require Software Engineers to Focus on Building Products

DevFeed: [Why Agentic Coding Tools Require Software Engineers to Focus on Building Products](<https://devfeed.tech/articles/become-builders-not-coders-29993.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2026/03/become-builders-not-coders/>)

Author: Michael Werle

Published: 2026-03-06T15:07:10Z

Content type: opinion

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [ai-coding](<https://devfeed.tech/topics/ai-coding.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [ide](<https://devfeed.tech/topics/ide.md>)

Tags: [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-culture](<https://devfeed.tech/tags/engineering-culture.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [sandboxing](<https://devfeed.tech/tags/sandboxing.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [unsorted](<https://devfeed.tech/tags/unsorted.md>)

### AI overview

This opinion article argues that software engineers should adapt to agentic coding tools by focusing less on manual coding and more on building products that solve customer problems. It describes the author's changing views on AI-assisted programming and highlights context engineering, MCP, skills, sandboxing, subagents, and related tools, while acknowledging significant security and automation risks.

### Source excerpt

Why agentic coding tools demand a new identity for software engineers After more than two decades of professional software engineering, I have arrived at a set of conclusions that I find very uncomfortable. The era of mostly manual coding has ended. IDEs, in their current form, are no longer necessary. Traditional software development languages are [...]

## Bringing Lighthouse to the App: Building Performance Metrics for React Native

DevFeed: [Bringing Lighthouse to the App: Building Performance Metrics for React Native](<https://devfeed.tech/articles/bringing-lighthouse-to-the-app-building-performance-metrics-for-react-native-29994.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2026/03/bringing-lighthouse-to-the-app-building-performance-metrics-for-react-native/>)

Author: Ben Cripps

Published: 2026-03-03T19:13:53Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [React Native](<https://devfeed.tech/topics/react-native.md>), [Mobile](<https://devfeed.tech/topics/mobile.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>), [Core Web Vitals](<https://devfeed.tech/topics/core-web-vitals.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [app-performance](<https://devfeed.tech/tags/app-performance.md>), [core-web-vitals](<https://devfeed.tech/tags/core-web-vitals.md>), [google](<https://devfeed.tech/tags/google.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [performance](<https://devfeed.tech/tags/performance.md>), [react-native](<https://devfeed.tech/tags/react-native.md>), [time-to-interactive](<https://devfeed.tech/tags/time-to-interactive.md>), [unsorted](<https://devfeed.tech/tags/unsorted.md>)

### AI overview

Indeed describes an open-source React Native repository for measuring Lighthouse-style performance metrics in mobile apps. The article explains adapting Core Web Vitals concepts to React Native, including Time to First Frame and Time to Interactive, to assess screen loading and interaction readiness.

### Source excerpt

At Indeed we've open sourced a new React Native repository which makes it simple to measure Lighthouse scores in your mobile apps. We think it will help other organizations better measure their app performance, especially for companies similar to Indeed who are transitioning from a web-first to an app-first approach. You can check out the [...]

## Normalized Entropy or Apply Rate? Evaluation Metrics for Online Modeling Experiments

DevFeed: [Normalized Entropy or Apply Rate? Evaluation Metrics for Online Modeling Experiments](<https://devfeed.tech/articles/normalized-entropy-or-apply-rate-evaluation-metrics-for-online-modeling-experiments-29992.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2025/11/normalized-entropy-or-apply-rate-evaluation-metrics-for-online-modeling-experiments/>)

Author: Megan Chen

Published: 2025-11-11T06:16:53Z

Content type: opinion

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [decision-making](<https://devfeed.tech/topics/decision-making.md>), [benchmarking](<https://devfeed.tech/topics/benchmarking.md>)

Tags: [a-b-testing](<https://devfeed.tech/tags/a-b-testing.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [decision-making](<https://devfeed.tech/tags/decision-making.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [metric](<https://devfeed.tech/tags/metric.md>), [models](<https://devfeed.tech/tags/models.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [unsorted](<https://devfeed.tech/tags/unsorted.md>)

### AI overview

Indeed examines whether model performance metrics or product metrics should guide online modeling experiments. It discusses how optimizing individual ranking models may not align with broader business goals and considers evaluation metrics for model rollouts.

### Source excerpt

Introduction At Indeed, our mission is to help people get jobs. We connect job seekers with their next career opportunities and assist employers in finding the ideal candidates. This makes matching a fundamental problem in the products we develop. The Ranking Models team is responsible for building Machine Learning models that drive matching between job [...]

## The Agentic Identity Journey: Building IAM for Autonomous Actors

DevFeed: [The Agentic Identity Journey: Building IAM for Autonomous Actors](<https://devfeed.tech/articles/the-agentic-identity-journey-29991.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2025/06/the-agentic-identity-journey/>)

Author: Ken Adler

Published: 2025-06-03T21:53:51Z

Content type: opinion

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [IAM](<https://devfeed.tech/topics/iam.md>), [identity and access management](<https://devfeed.tech/topics/identity-and-access-management.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Web](<https://devfeed.tech/topics/web.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-iam](<https://devfeed.tech/tags/agentic-iam.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [iam](<https://devfeed.tech/tags/iam.md>), [identity](<https://devfeed.tech/tags/identity.md>), [identity-and-access](<https://devfeed.tech/tags/identity-and-access.md>), [identity-and-access-management](<https://devfeed.tech/tags/identity-and-access-management.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [resilience](<https://devfeed.tech/tags/resilience.md>), [security](<https://devfeed.tech/tags/security.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

This commentary introduces Indeed's perspective on building an Agentic IAM architecture for a future in which autonomous and potentially malicious software agents interact with its platform. It emphasizes precise authorization, trustworthy delegation, verifiable auditing, speed, resilience, and privacy, and presents the post as the first entry in a series.

### Source excerpt

Every so often, the web changes in a way that rewires how we live. In the early days, Web 1.0 let us read. It was a window into information -- static pages, digital brochures, news sites. We were spectators peering into a new world. Then came Web 2.0, and we learned to write. We didn't [...]

## How Indeed Replaced Its CI Platform with Gitlab CI

DevFeed: [How Indeed Replaced Its CI Platform with Gitlab CI](<https://devfeed.tech/articles/how-indeed-replaced-its-ci-platform-with-gitlab-ci-29990.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2024/08/indeed-gitlab-ci-migration/>)

Author: Carl Myers

Published: 2024-08-06T15:03:51Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [GitLab](<https://devfeed.tech/topics/gitlab.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Jenkins](<https://devfeed.tech/topics/jenkins.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [Amazon EC2](<https://devfeed.tech/topics/amazon-ec2.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [aws](<https://devfeed.tech/tags/aws.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ec2](<https://devfeed.tech/tags/ec2.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [gitlab-ci](<https://devfeed.tech/tags/gitlab-ci.md>), [jenkins](<https://devfeed.tech/tags/jenkins.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [unsorted](<https://devfeed.tech/tags/unsorted.md>)

### AI overview

Indeed's engineering platform evolved from Hudson to Jenkins and later encountered architectural and scaling limitations as the company grew and adopted AWS EC2 and Kubernetes. The article discusses replacing that CI platform with GitLab CI.

### Source excerpt

Here at Indeed, our mission is to help people get jobs. Indeed is the #1 job site in the world with over 580M+ Job Seeker Profiles. For Indeed's Engineering Platform teams, we have a slightly different motto: "We help people to help people get jobs". As part of a data-driven engineering culture that has spent [...]

## Secure Workload Identity with SPIRE and OIDC: A Guide for Kubernetes and Istio Users

DevFeed: [Secure Workload Identity with SPIRE and OIDC: A Guide for Kubernetes and Istio Users](<https://devfeed.tech/articles/secure-workload-identity-with-spire-and-oidc-a-guide-for-kubernetes-and-istio-users-29989.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2024/07/workload-identity-with-spire-oidc-for-k8s-istio/>)

Author: Nikhil Arora

Published: 2024-07-03T15:52:26Z

Content type: tutorial

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [SPIRE](<https://devfeed.tech/topics/spire.md>), [istio](<https://devfeed.tech/topics/istio.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [OpenID connect (OIDC)](<https://devfeed.tech/topics/oidc.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>), [AWS Identity and Access Management (IAM)](<https://devfeed.tech/topics/aws-identity-and-access-management-iam.md>), [Architecture & Design](<https://devfeed.tech/topics/architecture-design.md>)

Tags: [authentication](<https://devfeed.tech/tags/authentication.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [aws-iam](<https://devfeed.tech/tags/aws-iam.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [guide](<https://devfeed.tech/tags/guide.md>), [identity](<https://devfeed.tech/tags/identity.md>), [istio](<https://devfeed.tech/tags/istio.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [oidc](<https://devfeed.tech/tags/oidc.md>), [secrets](<https://devfeed.tech/tags/secrets.md>), [spire](<https://devfeed.tech/tags/spire.md>), [unsorted](<https://devfeed.tech/tags/unsorted.md>), [zero-trust](<https://devfeed.tech/tags/zero-trust.md>)

### AI overview

This guide describes Indeed's approach to building a workload identity platform for Kubernetes and Istio using SPIRE and OIDC, with identities and access controls rooted in Zero Trust principles. It discusses credential risks, design choices, and implementation challenges for heterogeneous first-party and third-party workloads.

### Source excerpt

Goal This blog is for engineering teams, architects, and leaders responsible for defining and implementing a workload identity platform and access controls rooted in Zero Trust principles to mitigate the risks from compromised services. It is relevant for companies using Kubernetes to manage workloads, using Istio for service mesh, and aiming to define identities in [...]

## The Importance of Using a Composite Metric to Measure Performance

DevFeed: [The Importance of Using a Composite Metric to Measure Performance](<https://devfeed.tech/articles/the-importance-of-using-a-composite-metric-to-measure-performance-29988.md>)

Original publisher: [Read original article](<https://engineering.indeedblog.com/blog/2024/01/composite-web-performance-metric/>)

Author: Ben Cripps

Published: 2024-01-31T21:57:58Z

Content type: article

Language: en

Sources: [Indeed](<https://devfeed.tech/sources/indeed.md>)

Topics: [performance measurements](<https://devfeed.tech/topics/performance-measurements.md>), [client](<https://devfeed.tech/topics/client.md>), [Usability](<https://devfeed.tech/topics/usability.md>), [JavaScript](<https://devfeed.tech/topics/javascript.md>), [Google Analytics](<https://devfeed.tech/topics/google-analytics.md>)

Tags: [engineering](<https://devfeed.tech/tags/engineering.md>), [google-analytics](<https://devfeed.tech/tags/google-analytics.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-measurements](<https://devfeed.tech/tags/performance-measurements.md>), [usability](<https://devfeed.tech/tags/usability.md>)

### AI overview

Indeed examines the limitations of relying on a single client-side performance metric, including incomplete coverage of third-party content and poor alignment with actual usability. It suggests that a composite metric can better measure users' experience.

### Source excerpt

In the past, Indeed has used a variety of metrics to evaluate our client-side performance, but we've tended to focus on one at a time. Traditionally, we chose a single performance metric and used it as the measuring stick for whether we were improving or degrading the user experience. This made it simple to track [...]