Member of Technical Staff, Applied AI
About The Position
As a Member of Technical Staff, Applied AI, you will build dependable agents that move personal injury cases forward and automate repetitive, paper-based, and fragmented workflows. You will own critical features end-to-end, ship quickly, and work alongside strategy and operations, product, design, and legal teammates. The role includes building production-grade voice, browser, document, and workflow agents; designing long-horizon agent systems; and continuously improving agent quality using real cases and operator feedback. You will optimize performance and reliability across calls, documents, communications, and third-party portals, and evaluate and implement advances in agentic AI that improve quality, speed, or cost. The team works together in Finch’s NYC office four days a week. The hiring process generally includes an introductory conversation, a practical technical interview, and an onsite visit to the NYC office.
Requirements
- At least 2 years of experience building reliable, secure production software and the ability to own systems across the stack.
- Experience shipping AI-powered products or agents beyond the prototype stage.
- Experience designing practical evaluations 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 agent-design instincts, 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: move quickly, measure what matters, and prioritize whether an agent completes the job correctly.
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.
Responsibilities
- 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.
- Develop and own an evaluation flywheel by turning real cases and operator feedback into benchmarks that continuously improve agent quality.
- Optimize agent performance through model selection and routing, context engineering, prompting, tool design, and agent observability.
- Make agents reliable across calls, documents, communications, and third-party portals, including when systems fail or case information changes.
- Evaluate advances in agentic AI and rapidly ship those that improve quality, speed, or cost.
- Own critical features end-to-end and deliver dependable systems from ambiguous, real-world workflows.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
