TL;DR
AI Engineer (Agent Team): Developing orchestration and reasoning systems for AI agents in the insurance industry with an accent on agent performance evaluation and multi-agent system architecture. Focus on building reliable production-grade tools, experimenting with advanced prompting techniques, and scaling agentic workflows on top of existing LLMs.
Location: Must be based in or able to work onsite in San Francisco, USA
Salary: $150,000 – $250,000 + equity
Company
A high-growth AI startup building next-generation insurance automation agents with strong backing from top investors like a16z and YC.
What you will do
- Design and implement end-to-end evaluation frameworks to measure and optimize agent performance.
- Experiment with and integrate advanced agentic techniques such as multi-agent systems and reasoning-from-feedback.
- Build robust orchestration layers and lightweight server tools to enable reliable agent production usage.
- Translate emerging LLM research into functional production experiments.
Requirements
- 3+ years of professional experience building in ML/AI.
- Strong proficiency in Python.
- Proven ability to communicate complex technical concepts clearly.
- High degree of drive, grit, and ownership.
- Must be able to work onsite in San Francisco.
Nice to have
- Previous experience in B2B SaaS.
- Experience in 0 to 1 product development environments.
Culture & Benefits
- Fully covered health, dental, and vision insurance.
- Meaningful stock options and company 401(k) plan.
- Unlimited PTO policy.
- On-site lunch and dinner provided daily.
- Vibrant in-office culture with regular team events and off-sites.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →