Staff Software Engineer - Strategic Agentic Surfaces

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, RelativityOne, 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. WHAT WE DO 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 and works with the broader Relativity technology organization on shared AI platform decisions, security and compliance reviews, and integrations with Relativity’s litigation surfaces. Job Description and Requirements ABOUT THE ROLE As the Staff Software Engineer for Gavel Exec, you will serve as the full-stack technical owner of the product and its agentic architecture. You will set the direction for the harness, context pipeline, and evaluation system over the next two to three years and own the quality bar that enables lawyers to trust the output. You will work directly with Gavel’s CTO on architecture, amplify the effectiveness of the engineering team, and represent Gavel engineering across the broader Relativity technology organization. Level: Staff, the senior-most individual contributor on the team Reports to: Pierre Martin, CTO of Gavel and VP of Engineering at Relativity Location: Remote within the United States, Seattle, or Chicago WHAT YOU’LL DO Own the architecture of the Gavel Exec agent system, including dispatcher and specialist agents, tool interfaces, harness semantics, retries, structured outputs, guardrails, cost and latency budgets, and the boundary between deterministic and model-driven logic. Set the evaluation strategy by defining quality standards for each agent, building offline evaluation infrastructure and online acceptance-rate instrumentation, and using evaluation results to gate releases. Lead the full technical roadmap across the stack, including live indexing, hybrid search, and playbook and precedent grounding. Drive platform decisions with Relativity, including infrastructure footprint, identity, tenancy, data residency, integration with the broader AI platform and MCP surfaces, and enterprise security requirements. Drive a modern software development lifecycle that supports high-quality, high-velocity delivery through best-in-class agentic engineering tools and practices. Raise the engineering bar through design reviews, pairing, and written technical direction. Mentor Lead and Senior engineers, help define the technical hiring loop, and interview senior candidates. Remain hands-on and ship continuously, especially on the hardest and highest-leverage problems. WHAT WE’RE LOOKING FOR 10+ years of experience building production software, including at least 2 years shipping LLM-based products to real users and at least 5 years in a service-oriented, continuously deployed environment. Demonstrated ownership of an agentic system in production, including multi-step tool use, orchestration across specialist components, failure handling, tracing, cost, latency, and incident response. Deep, practical understanding of the modern AI engineering stack, including prompt and context engineering, structured outputs, function calling, retrieval, reranking, evaluation design, fine-tuning trade-offs, and model routing across providers. Strong distributed systems fundamentals and hands-on cloud infrastructure experience, with AWS or Azure experience or a willingness to develop deep expertise quickly. Experience with containers, CI/CD, infrastructure as code, and enterprise identity. Fluency in TypeScript or Python and the ability to work across a React frontend, Node or Python services, and PostgreSQL. Direct experience building full-stack web applications and agentic applications. A track record of setting technical direction that strong engineers follow and communicating complex trade-offs clearly to product, business, and security stakeholders. A strong commitment to simplicity and sound judgment about when abstractions add value. WHY WE COULD BE A GREAT FIT Build systems that help customers organize data, discover the truth, and act on it in high-stakes legal matters. Work on distributed, cloud-native systems that process large volumes of data. Build with AI, cloud platforms, and scalable architectures shaping legal tech. Gain experience owning systems end-to-end across cloud and distributed environments. Work in a team focused on knowledge sharing and continuous improvement. Diverse perspectives create stronger teams and better outcomes. Compensation and Benefits Competitive salary, benefits, DTO, parental leave, and equity program. Competitive base salary, an annual performance bonus, and long-term incentives. Relativity is committed to competitive, fair, and equitable compensation practices. This position is eligible for total compensation which includes a competitive base salary, an annual performance bonus, and long-term incentives. The expected salary range for this role is between following values:$174,000 and $262,000. The final offered salary will be based on several factors, including but not limited to the candidate's depth of experience, skill set, qualifications, and internal pay equity. Hiring at the top end of the range would not be typical, to allow for future meaningful salary growth in this position. Required Skills:Algorithms, Automation, Debugging, Distributed Systems, Performance Tuning, Problem Solving, Project Management, Software Development, System Designs, Technical Leadership #J-18808-Ljbffr