Experience:

• 3+ years of software engineering experience
• At least 1 year building production LLM-powered systems or agents used by real users

Responsibilities:

• Build production-quality LLM-powered systems or agents
• Write maintainable, tested, production-quality Python services
• Use LLM APIs including tool use, function calling, structured outputs, streaming, prompt caching, and multi-turn context handling
• Work with agent/orchestration frameworks or custom orchestration
• Integrate REST APIs and webhooks across various tools
• Define success metrics and evaluate LLM performance
• Create feedback loops and iterate from telemetry
• Operate services in production with Docker, CI/CD, observability, logging, and alerts
• Query logs, deploy events, incident timelines, accuracy signals, and time-series reliability data using SQL and BigQuery
• Write clear design documents defining scope, non-goals, evaluation methodology, owners, and risks

Additional responsibilities:

• Collaborate within a fast-growing, interactive, and adaptive work culture
• Contribute to a mission-driven environment fostering inclusion, empowerment, accountability, and fun

More skills:

LLM APIs, Webhook integration, Slack, Jira, Linear, Notion, PagerDuty, Docker, CI/CD, Observability, Logging, Alerts, SQL, BigQuery, Machine Learning, NLP

Other:

• Founded in 2020
• Company size 10 - 50 employees
• Backed by YCombinator
• Focus on reducing administrative hassles and maximizing revenue for healthcare providers
• Interview process includes online coding test and in-person technical rounds with senior engineers and leadership
• Exceptional total compensation
• Work with a world-class team on a forward-looking healthcare problem
• Leading healthcare benefits