Sourcegraph

2 weeks ago

Agent Engineer [IC4]

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 9 hours agoStatus: Live

Job Summary

Own agent engineering for the Code Understanding team’s developer intelligence surfaces, including Deep Search and related agentic experiences. Design and harden multi-step tool-using agent loops, apply pragmatic evaluation strategies, and drive model selection, upgrading, and fine-tuning. Improve retrieval and context engineering (citations, ranking, context windows) while treating cost and latency as product features.

Location: Anywhere

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and harden multi-step, tool-using agent loops behind current and new agentic experiences.
•Create evaluation strategies (e.g., smoke tests and metrics) to measure whether changes truly improve product quality.
•Own model selection, upgrading, and fine-tuning decisions for agentic systems.
•Advance retrieval and context engineering to make answers more accurate and verifiable (e.g., citations, context windows).
•Profile, distill, cache, and right-size models to improve cost and latency as product features.

Pay and Benefits

Salary: USD 88,000 annually

Equity and Bonus:Equity

Key Requirements

•Build, train, evaluate, and operate models in production with strong grounding in datasets, evals, baselines, metrics, and error analysis.
•Design reliable, observable, cost-bounded multi-step agentic systems and have a clear point of view on when agents vs deterministic code are appropriate.
•Use evaluations pragmatically, including lightweight smoke tests and real-world feedback, while holding cost and latency as constraints.
•Operate autonomously on ambiguous, high-technical-risk problems and deliver plans, prototypes, milestones, and tradeoffs end-to-end.
•Be a strong software engineer able to ship production services and work across the stack, including backend and frontend.

Skills:Technical leadershipMentorshipCollaborationJudgmentProblem-solving

Languages:English

Tech Stack:GoTypeScriptGraphQLPostgresDockerLLMMachine learningRetrievalEmbeddingsRankingFine-tuningDistillation

Company Brief

Sourcegraph

Provides universal code search and intelligence for developers and engineering teams, enabling fast code navigation, cross-repository search, code intelligence, and developer productivity tooling for both cloud and self-hosted environments.

Industry: Developer Tools

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series D

Headquarters: San Francisco, United States

Founded: 2013

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Sourcegraph

2 weeks ago

Agent Engineer [IC4]

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 9 hours agoStatus: Live

Job Summary

Location: Anywhere

Workplace: Remote

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Design and harden multi-step, tool-using agent loops behind current and new agentic experiences.
•Create evaluation strategies (e.g., smoke tests and metrics) to measure whether changes truly improve product quality.
•Own model selection, upgrading, and fine-tuning decisions for agentic systems.
•Advance retrieval and context engineering to make answers more accurate and verifiable (e.g., citations, context windows).
•Profile, distill, cache, and right-size models to improve cost and latency as product features.

Pay and Benefits

Salary: USD 88,000 annually

Equity and Bonus:Equity

Key Requirements

•Build, train, evaluate, and operate models in production with strong grounding in datasets, evals, baselines, metrics, and error analysis.
•Design reliable, observable, cost-bounded multi-step agentic systems and have a clear point of view on when agents vs deterministic code are appropriate.
•Use evaluations pragmatically, including lightweight smoke tests and real-world feedback, while holding cost and latency as constraints.
•Operate autonomously on ambiguous, high-technical-risk problems and deliver plans, prototypes, milestones, and tradeoffs end-to-end.
•Be a strong software engineer able to ship production services and work across the stack, including backend and frontend.

Skills:Technical leadershipMentorshipCollaborationJudgmentProblem-solving

Languages:English

Tech Stack:GoTypeScriptGraphQLPostgresDockerLLMMachine learningRetrievalEmbeddingsRankingFine-tuningDistillation

Company Brief

Sourcegraph

Industry: Developer Tools

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series D

Headquarters: San Francisco, United States

Founded: 2013

Website LinkedIn