Member of Technical Staff, Applied AI

ABOUT FINCH We believe every American household deserves access to counsel in life’s biggest moments. At Finch, we’re building the infrastructure to make justice radically more accessible. Our modern approach to consumer law automates the admin work and puts clients first, starting with personal injury. In just over a year, we've grown 10x, raised a $20M Series A, and become the pre-litigation partner of choice for top personal injury firms across the country. We believe the best outcomes happen when expert operators and purpose-built AI work together – which is why we handle every step of pre-lit, from intake and claim opening to medical records, lien management, and demands, with humans leading every case. We’re backed by Sequoia, Redpoint, and the founders & CEOs of generational companies like DoorDash, Ironclad, and Digits. We’re rebuilding how the law serves everyday Americans from first principles, and we’re hiring exceptional operators to help us scale it nationwide. THIS ROLE Personal injury law is drowning in repetitive tasks, paper-based bottlenecks, and fragmented data – and we're building the software to fix it. As a Member of the Technical Staff at Finch, you'll own critical features end-to-end, ship fast, and work directly alongside product, ops, and design in a codebase where your decisions matter from day one. WHAT YOU'LL DO As a Member of the Technical Staff at Finch, you're building the system our team uses every day to run intake, medical records, police reports, lien management, and demands for personal injury firms across the country. Your code directly determines how many cases our paralegals can handle, and by extension, our ability to help more cases seen. This is a full-stack role at a company where the product is evolving quickly and engineers have real ownership – expect the scope to grow as we do. - Build production-grade voice, browser, document, and workflow agents that move personal injury cases forward. - Design long-horizon agent systems - including context, tools, memory, permissions, structured outputs, and human-in-the-loop controls. - Own the eval flywheel: turn real cases and operator feedback into benchmarks that continuously improve agent quality. - Optimize performance through model selection and routing, context engineering, prompting, tool design, and agent observability. - Make agents reliable across calls, documents, communications, third-party portals, partial failures, and changing case information. - Evaluate advances in agentic AI and rapidly ship the ones that improve quality, speed, or cost. WHO WE HAVE IN MIND This role is for technical team members who want ownership over outcomes, not just tickets. Here's what that requires. MUST-HAVES - 3+ years building reliable, secure software in production, with the ability to own systems across the stack. - Experience shipping AI-powered products or agents beyond the prototype stage. - Experience designing practical evals and using them to understand agent behavior, compare approaches, and improve task-completion quality. - Proficiency in Python and comfort working with React, LLM APIs, and agent frameworks. - Strong instincts for agent design, including context construction, model selection, tool boundaries, structured outputs, failure recovery, and human handoffs. - A track record of turning ambiguous, real-world workflows into simple, dependable systems. - An experimental mindset: you move quickly, measure what matters, and care more about whether an agent completes the job correctly than whether the approach is clever. NICE-TO-HAVES - Experience with Pydantic AI or another production agent framework. - Experience building voice agents, browser agents, or long-running workflow agents. - Familiarity with Django, React, Temporal, Playwright, or AWS. - Experience building evaluation systems, agent observability, model routing, or human-in-the-loop review tools. - Familiarity with legal tech, healthcare workflows, document processing,…