Job Summary
Own and improve a multi-agent research system, with a focus on making its LLM infrastructure reliable, responsive, and cost-efficient. You will develop evaluation frameworks, support the growth of other engineers, and take on broader leadership of the AI engineering team as the function expands.
Responsibilities
- Operate and optimize the multi-agent research system and its underlying LLM infrastructure.
- Improve system reliability, latency, and inference cost efficiency.
- Build evaluation frameworks to assess and strengthen system performance.
- Mentor engineers and, as the organization grows, lead the AI engineering team.
Qualifications
- At least 7 years of software or machine learning engineering experience.
- At least 3 years of experience delivering LLM-powered systems in production.
- Deep knowledge of inference economics and strong Python expertise.
- A demonstrated record of building and leading technical teams.

