Agent Engineer

Role Description

Sourcegraph is at the forefront of building AI tools to solve the biggest problems in the software industry. The Code Understanding team owns the surfaces where that intelligence meets the developer:

• Deep Search: our agentic, multi-step answer engine across an enterprise's entire lineup of codebases.
• Query Assist: turning natural language queries into Sourcegraph query syntax.
• Smart Hovers: concisely summarizing symbols right where devs need it.
• Guided diff review and the APIs that both humans and AI agents rely on every day.

As the senior agent engineer on Code Understanding, you'll be the technical owner, setting the agentic direction for the team, making our products better, faster, and cheaper.

Concretely, you'll own work like:

• Designing and hardening the multi-step, tool-using agent loops.
• Crafting agentic products and determining when evaluations are necessary.
• Deciding which models to run, driving upgrades, and fine-tuning.
• Improving retrieval and context engineering for more accurate answers.
• Managing cost and latency as product features.

You'll do this on a small, senior-leaning team that ships quickly, owns a lot of product surface, and has streamlined product management.

Within one month, you will:

• Get the Code Understanding products and their model/agent pipelines running end-to-end locally.
• Build a clear picture of where the AI engineering pain is.
• Get to know the team and our customers.
• Join the team's on-call support rotation.

Within three months, you will:

• Own a meaningful agentic slice of the product end-to-end.
• Establish how the team ships model and prompt changes responsibly.
• Begin up-leveling teammates in building with models.

Within six months, you will:

• Be the recognized technical authority for agent engineering.
• Have measurably moved the products: better answer quality, lower cost/latency, or new capabilities.
• Set the direction of the team's roadmap where it intersects agents.

Qualifications

• Senior engineer and technical leader with skills in agent engineering.
• Real agent engineering depth with experience in building, training, and evaluating models.
• Experience designing multi-step agentic systems.
• Pragmatic about evaluations and conscious of cost.
• Ability to operate autonomously on ambiguous problems.
• Contribute beyond your domain and up-level the people around you.
• Customer and product-driven mindset.
• Strong software engineering fundamentals.

Requirements

• Comfortable across the tech stack: Go, TypeScript, GraphQL, Postgres, Docker.
• Fluent with agentic coding tools.
• Experience in an async-first, multi-service, fast-paced remote environment.

Benefits

• Above-average salary.
• Equity options.
• Generous perks and benefits.

Interview Process

• Introduction Stage: Initial conversations to get to know you better.
• Recruiter Screen: 30 minutes.
• Hiring Manager Screen / Resume Deep Dive: 45 minutes.
• Team Interview Stage: In-depth experience discussions with team members.
• Technical Interviews: Two 60-minute sessions.
• Cross-functional team collaboration / Values: 60 minutes.
• Final Interview Stage: Understanding of business and values.
• Reference checks and background check.