Member of Technical Staff, Applied AI

The role

You will build production-grade voice, browser, document, and workflow agents for personal injury law. You will own critical features end-to-end and design long-horizon agent systems.

What you will do

• Build production-grade voice, browser, document, and workflow agents
• Design long-horizon agent systems including context, tools, memory, permissions, structured outputs, and human-in-the-loop controls
• Own the eval flywheel by turning real cases and operator feedback into benchmarks
• Optimize performance through model selection, routing, context engineering, prompting, tool design, and agent observability
• Make agents reliable across calls, documents, communications, and third-party portals
• Evaluate advances in agentic AI and ship improvements to quality, speed, or cost

Required qualifications

• 2+ years of experience building reliable, secure software in production
• Ability to own systems across the stack
• Experience shipping AI-powered products or agents beyond the prototype stage
• Experience designing practical evals to understand agent behavior and improve task-completion quality
• Proficiency in Python
• 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
• Track record of turning ambiguous, real-world workflows into simple, dependable systems
• Experimental mindset

Nice to have

• 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

Before you apply

• Intro conversation about background, motivation, and role
• Technical interview with an engineer
• Onsite visit to NYC office to interview, meet the team, and have lunch

About the company

Finch is building an applied AI platform for consumer law. The platform combines AI agents and legal operators to reduce manual work and expand access to justice.