About the role
We're looking for a Software Engineer who wants to build production-grade AI agents from the ground up. You will own a complete workstream within a personal injury case and turn it into a reliable autonomous agent. You'll work across LLMs, agent architecture, integrations, evaluation, reliability, and voice interactions. This is a high-ownership role where you'll work directly with founders, customers, and a small team of experienced builders.
Responsibilities:
- Build and ship production-grade LLM/AI agents capable of running autonomously for weeks.
- Design agent systems covering state, memory, retries, recovery, escalation, and decision-making.
- Build integrations across legal case management systems (CMS) such as Clio, Filevine, Litify, MyCase, and other third-party platforms.
- Develop clean abstractions over fragmented APIs, legacy systems, and customer-specific configurations.
- Build evaluation frameworks and regression testing using transcripts/traces to continuously improve agent reliability.
- Improve AI agent conversations and voice interactions, ensuring agents communicate naturally and effectively.
- Work closely with customers to understand their workflows and onboard new firms quickly.
- Own your workstream end-to-end from architecture and implementation to production performance.
Requirements:
- Experience building and shipping LLM/AI agents in production with real users.
- Strong understanding of agentic AI, LLMs, AI workflows, or autonomous systems.
- Experience building evaluation frameworks, regression testing, or transcript/trace-based testing for AI systems.
- Strong experience integrating third-party APIs, SaaS platforms, or legacy systems.
- Ability to build scalable abstractions over complex and fragmented systems.
- Strong product mindset: you care about how the AI behaves and interacts with users, not just whether the code works.
- Strong ownership and ability to work independently in a fast-paced startup environment.
- Comfortable working closely with customers and founders.
- Key Skills: Agentic AI, LLM, Generative AI, AI Agents, Python, API Integrations, SaaS Integrations, AI/ML, Evaluation Frameworks, Regression Testing, Voice AI, Workflow Automation, Third-party APIs, Production AI Systems.