About Finch

Our mission is to make justice radically more accessible to every American household.

We combine expert operators with purpose-built AI to automate the admin work of consumer law and put clients first by handling intake, claim opening, medical records, police reports, lien management, demands, and everything in between.

Since launching in April 2025, we’ve raised a $20M Series A backed by Sequoia, Redpoint, and the founders & CEOs of DoorDash, Ironclad, and Digits and are running pre-litigation for over 125 of the highest-volume personal injury firms across the country.

Explore life at Finch for more.

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

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 - here's what we think 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, or other operationally complex domains.

This Role Might Not Be For You If

• You do your best work with a well-defined spec and a stable, established codebase.

• You prefer deep specialization in one layer of the stack over full-stack ownership.

• You're looking for a remote-first role – this one is 4 days/week in our NYC office.

Benefits

• 100% coverage for health, dental, and vision.

• 401(k) retirement plan.

• In-office snacks, drinks, and daily team lunches and dinners.

• Flexible PTO (we trust you to take the time you need).

Interview Process

1. Intro: An initial call to see if there's a mutual fit.

2. Interview: Technical session with a member of the team.

3. Onsite: A visit to our NYC office to interview, meet the team, and have lunch.