Lead Software Engineer - AI Surfaces

Relativity is hiring a hands-on technical leader to own a major area of Gavel’s AI surfaces. In this role, you will set the technical direction across the front end, the harness layer, and the data layer, guiding execution from roadmap planning through evaluation, releases, and production monitoring.

As the Lead Software Engineer for AI Surfaces, you will partner closely with Relativity leadership, product, design, shared platform/security teams, and the broader engineering org to plan what to build next and ensure it ships with measurable quality.

What you’ll do

• Own the technical roadmap and delivery for your area, covering the full flow from design through production monitoring.
• Translate ambiguous product goals into shippable milestones and sequence work across the stack.
• Design and build agents and the infrastructure that runs them, including tool definitions, prompts and context assembly, structured outputs, guardrails, evaluation sets, and the Word and web experiences that surface agent capabilities.
• Operate the evaluation and release loop for your agents.
• Use acceptance rates to diagnose changes in outcomes, determine readiness to ship, and drive decisions based on results.
• Model a modern development lifecycle for your squad using small, frequent commits, feature-flagged production deployments, fast rollbacks, and daily use of agentic engineering tools to improve both quality and velocity.
• Collaborate directly with Dorna Moini, Pierre Martin, product, and design on the next build, and engage with customers when the next step is not obvious from available data.
• Lead design reviews, define coding and testing standards for the squad, mentor Senior and Advanced engineers, and participate in hiring.
• Partner with Relativity platform and security teams on topics that involve shared infrastructure, identity, or compliance.

What you bring

• 8+ years of experience building production software in service-oriented, continuously deployed teams, including at least 1 year shipping LLM-based products or features to real users.
• Direct experience building full-stack web applications and agentic applications, including ownership of at least one agentic capability in production involving tool use and function calling, multi-step orchestration, structured outputs, retries and failure handling, and observation and debugging of non-deterministic systems.
• Practical evaluation experience, including building evaluation sets, selecting metrics, applying LLM-as-judge appropriately, and connecting offline results to online outcomes.
• Strong understanding of retrieval and context engineering, including embeddings, hybrid search, chunking, ranking strategies, and context budgeting.
• Hands-on cloud experience with AWS or Azure, or readiness to develop deep expertise quickly, plus comfort with containers, CI/CD, infrastructure as code, and production observability.
• Fluency in at least one of TypeScript or Python, with the ability to work across the stack including React front ends, Node or Python services, and PostgreSQL.
• Experience leading technical work for a small team through planning, reviews, unblocking, and engineering development while continuing to contribute meaningful code.
• Clear written and verbal communication, including the ability to explain model-quality regressions to lawyers and scoping trade-offs to founders.
• Strong drive for simplicity, with judgment to separate useful abstractions from unnecessary complexity.

Technologies

• TypeScript, Python, React, Node, PostgreSQL
• AWS, Azure
• Containers, CI/CD, infrastructure as code
• LLM-as-judge, embeddings, hybrid search, chunking, ranking strategies

Compensation and benefits

• Competitive salary, benefits, DTO, parental leave, and an equity program.
• Annual performance bonus.
• Long-term incentives.
• Expected salary range: USD 150,000 to 224,000 per year.

Location: Illinois (hybrid). Posting type indicates may be based remotely in the United States or in Seattle or Chicago.