Member of Technical Staff

Responsibilities

• Build production-grade voice, browser, document, and workflow agents for personal-injury case workflows.
• Design agent systems with context construction, tools, memory, permissions, structured outputs, failure recovery, and human handoffs.
• Create evaluation benchmarks from real cases and operator feedback to improve agent quality and task completion.
• Optimize agents through model selection, routing, context engineering, prompting, tool design, and observability.
• Make agents dependable across calls, documents, communications, and third-party portals.
• Evaluate and rapidly ship agentic AI advances that improve quality, speed, or cost.
• Own critical features end-to-end and collaborate with strategy and operations, product, design, and legal teams.

Requirements

• At least 2 years of experience building reliable, secure production software and owning 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.
• Proficiency in Python and comfort with React, LLM APIs, and agent frameworks.
• Strong agent-design judgment involving context, model selection, tool boundaries, structured outputs, failure recovery, and human handoffs.
• Ability to turn ambiguous real-world workflows into simple, dependable systems.
• Experience with Pydantic AI or another production agent framework is a plus.
• Experience with voice agents, browser agents, long-running workflow agents, evaluation systems, agent observability, model routing, or human-in-the-loop review tools is a plus.
• Familiarity with legal technology, healthcare workflows, document processing, or other operationally complex domains is a plus.

Benefits

• Work from the NYC office four days per week; this is not a remote-first role.
• High ownership and freedom to shape product solutions.
• Direct impact on real personal-injury cases and close collaboration with users.
• Opportunity to work on applied AI and experiment with agentic systems.
• Interview process generally includes an introductory conversation, technical interview, and onsite visit.