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 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. Most of what makes those surfaces tick is agent engineering: a blend of software engineering, machine learning, and statistics.

Responsibilities

• Design and harden the multi-step, tool-using agent loops behind current and new agentic experiences.
• Craft agentic products and evaluate their effectiveness.
• Decide which models to run, drive upgrades, and fine-tune models.
• Push on how we ground models in a customer's code.
• Treat cost and latency as product features and optimize them.

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.

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 and agentic systems.
• Have measurably moved the products: better answer quality, lower cost/latency, or new agentic capabilities.
• Set the direction of the team's roadmap where it intersects agents.

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. You have real agent engineering depth, having built, trained, evaluated, and operated models in production. You are comfortable reasoning about evaluations, datasets, and metrics. You operate autonomously on ambiguous problems and contribute beyond your domain. You are customer and product-driven, comfortable on customer calls, and you push back when feedback would lead the product astray.

Engineering fundamentals

You are a strong software engineer who can ship production services. You are comfortable across our stack - Go on the backend, TypeScript on the frontend, GraphQL, Postgres, Docker.

Nice-to-haves

• Experience shipping an LLM-powered or agentic developer-facing product.
• Experience building evaluation systems for LLM or ML products.
• Experience mentoring or up-leveling engineers.

Level

This job is an IC4. You can read more about our job leveling philosophy in our Handbook.

Compensation

The target compensation for this role is based on the IC4 pay band for your zone. The start of the IC4 pay band for each zone is listed below:

• Zone 2: $176,000 USD
• Zone 3: $132,000 USD
• Zone 4: $88,000 USD

In addition to our cash compensation, we offer equity and generous perks & benefits.