Senior Software Engineer - AI Surfaces

Hybrid/Remote

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 the 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, with product and engineering led directly by Dorna Moini, CEO, and Pierre Martin, CTO of Gavel and VP of Engineering at Relativity.

As a Senior Software Engineer, you will build and own production agents end to end across the full stack. You will take agents from customer problems and rough specifications through tool design, prompt and context work, evaluation sets, Word or web experiences, feature-flagged launches, and follow-up improvements informed by acceptance data. You will work independently on well-scoped problems and collaboratively on ambiguous ones, directly with the founders and the rest of the team.

Level: Senior

Reports to:

Lead or Staff Engineer, Gavel at Relativity

Location:

Remote within the United States, Seattle, or Chicago

• Design, build, and ship agents and agent capabilities end to end, including tools, prompts, context assembly, structured outputs, guardrails, services, and the frontend experience in Word or on the web.
• Build and maintain evaluations for the capabilities you own. Use them to guide decisions and instrument production to measure acceptance, latency, and cost per agent.
• Contribute to shared infrastructure, including the harness, context and retrieval pipeline, model routing, and observability stack.
• Practice a modern software development lifecycle through small, frequent commits, feature-flagged production deployments, fast rollbacks, and daily use of agentic engineering tools.
• Debug non-deterministic failures, retrieval misses, tool-call errors, and model regressions.
• Participate in design reviews, write clear technical documentation, review code for other engineers, and mentor Advanced engineers.
• Work directly with product, design, and, at times, customers to understand what good work product means for a given legal task.

• 5+ years of experience building production software in service-oriented, continuously deployed teams, including experience shipping LLM-powered features to real users through a launched project, not only experiments.
• Direct experience building full-stack web applications and agentic applications, including API usage across providers, function calling and structured outputs, prompt and context engineering, retrieval-augmented generation, and evaluation fundamentals.
• Hands-on cloud service development experience with AWS, Azure, or an equivalent platform, including containers, CI/CD, and production debugging, with a willingness to develop deep expertise.
• Fluency in Type Script or Python and the ability to work across a React frontend, Node or Python services, and PostgreSQL.
• Experience writing and maintaining tests that catch regressions.
• Strong engineering fundamentals in API design,…