Lead Software Engineer - AI Surfaces

Hybrid/Remote

WHO WE ARE Relativity is a leading legal data intelligence company building technology that helps users organize data, discover the truth, and act on it with confidence. Our AI-powered, cloud platform, Relativity One, transforms massive volumes of complex information into actionable insights for litigation, investigations, regulatory inquiries, data breach responses, and other high-stakes legal work where accuracy and trust are crucial.

The world’s largest law firms, corporations, and government agencies rely on Relativity’s legal AI software to securely surface and manage the most relevant and impactful information in their matters. Beyond our commercial impact, we are committed to expanding access to technology and supporting pro bono legal work.

Gavel is a Microsoft Word-native agentic surface where lawyers perform real-time, evidence-based document editing and drafting. Gavel operates as a small, founder-led team within Relativity, connecting its product and engineering work with Relativity teams responsible for shared platform capabilities, identity, and security.

As a Lead Software Engineer, you will be the full-stack technical owner for a major area of Gavel’s product, such as a family of agents or a core capability including the context pipeline, evaluation platform, or Word integration. You will own the technical plan across the front end, harness, and data layer, along with the quality of releases and the growth of the two to four engineers building the area with you.

• Own the technical roadmap and delivery for your area, from design through production monitoring. Break ambiguous product goals into shippable milestones and sequence them across the stack.
• Design and build agents and the infrastructure they run on, including tool definitions, prompts and context assembly, structured outputs, guardrails, evaluation sets, and the Word and web experiences that surface them.
• Run the evaluation and release loop for your agents. Understand acceptance rates, identify why results change, and determine whether a change is ready to ship.
• Model a modern software development lifecycle for your squad through small, frequent commits, feature-flagged production deployments, fast rollbacks, and daily use of agentic engineering tools to improve quality and velocity.
• Partner directly with Dorna Moini, Pierre Martin, product, and design on what to build next, and engage with customers when the answer is not clear from the data.
• Lead design reviews, establish coding and testing standards for your squad, mentor Senior and Advanced engineers, and participate in hiring.
• Work with Relativity platform and security teams on areas that touch shared infrastructure, identity, or compliance.

• 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 experience with evaluation, including building evaluation sets, selecting metrics, using LLM-as-judge appropriately, and connecting offline results to online outcomes.
• A solid grasp of retrieval and context engineering, including embeddings, hybrid search, chunking and ranking strategies, and context budgeting.
• Hands‑on cloud infrastructure experience with AWS or Azure, or the willingness to…