Agent Engineer [IC4]

Who we are

Everything is changing in how software gets built, and Sourcegraph is at the center of that transformation. With Code Search, Deep Search, and MCP, Sourcegraph is the world’s most powerful code intelligence platform that developers and agents rely on to navigate, understand, and operate on massive, complex codebases with speed and confidence. Teams at companies like Stripe, Uber, and Dropbox rely on Sourcegraph to ship faster and with higher quality. We’re backed by a16z, Sequoia, and Redpoint, and proud to operate as a globally distributed team that values high agency, direct communication, and a deep love for developers and their craft. If you want to contribute to infrastructure that empowers millions of developers to do their best work - join us.

Why this job is exciting

Sourcegraph is at the forefront of building AI tools to solve the biggest problems in the software industry, problems that only get bigger as codebases grow and as more of the work is done by agents. 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 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. Most of what makes those surfaces tick is agent engineering: a blend of software engineering, machine learning, and statistics. Agent engineering tells us which model to use and when, how to retrieve and pack context, how to measure answer quality, where to fine-tune or distill a smaller model to cut costs and latency, and how to expand a single LLM call into a reliable multi-step agent.

Concretely, you'll own work like:

• Agentic systems. Design and harden the multi-step, tool-using agent loops behind current and new agentic experiences, turning research and experiments into reliable, observable, and affordable products at enterprise scale.
• Pragmatic use of evaluations. Crafting agentic products means needing to tell when a change actually helped, which is hard when agents keep changing and the product keeps shifting. Bring judgment about where evaluations earn their keep, when to use targeted smoke tests and metrics, and how to avoid noise dressed up as rigor, so we can move fast with confidence.
• Models: selection, upgrading, and training. Decide which models we run where, drive upgrades, and fine-tune our own when that's the right call.
• Retrieval and context engineering. Push on how we ground models in a customer's code - retrieval, ranking, context windows, citations - to make answers more accurate and verifiable.
• Cost and latency. Every surface has a per-user economic budget. Treat cost and latency as product features, and profile, distill, cache, and right-size models so we can ship ambitious features sustainably. Operate on a small, senior-leaning team that ships quickly, owns a lot of product surface, and has streamlined product management: engineers here talk to customers, frame the problem, and own it end-to-end.

About You

You are a senior engineer and technical leader with hard-won skills in agent engineering - a blend of software engineering, machine learning, and statistics. This is a senior, high-leverage role that relies on your real agent engineering judgment applied to a fast-moving product, plus the ability to collaborate on steering technical direction and to be a force multiplier for a talented, product-minded team. You're equally comfortable reasoning about an eval harness, a fine-tuning run, a retrieval pipeline, and the multi-step agent loop that ties them together, and you make everyone around you better at all of it. You operate at staff scope: you own the most ambiguous, highest-risk problems in your domain, go into whatever codebase a problem requires, set standards and patterns others adopt, and translate fluidly between engineering goals and business objectives. You influence direction beyond your immediate team. You lead through technical excellence and mentorship. You have real agent engineering depth. You've built, trained, evaluated, and operated models in production. You think naturally in terms of datasets, evals, baselines, metrics, and error analysis, and you know how to tell whether a change actually made things better.

On the engineering fundamentals:

• You're a strong software engineer who can ship production services.
• You're comfortable across our stack - Go on the backend, TypeScript on the frontend, GraphQL, Postgres, Docker - or you're clearly able and eager to get there.
• You're fluent with agentic coding tools, and you understand and own every line it submits.
• You're comfortable in an async-first, multi-service, fast-paced remote environment.