Staff AI Engineer, Agents and Evals
New
M
MimoLabsAI manufacturing
Remote across the USFull-TimeStaff
Salary$170K–$220K base and equity, four-year vesting with a one-year cliff.
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonRegression testingPrompt Engineering
Requirements
- Have experience with agent systems in production, including tool use, multi-step loops, streaming, and failure recovery, with demonstrable results.
- Have built graded evaluation suites, regression gates, and human review processes before trusting a change.
- Have context engineering experience with prompts, retrieval, and memory managed as one budget, with costs measured.
- Design reliable tool contracts, including schemas, results, and errors.
- Use Python.
- Have either worked with a large production codebase with a strict test baseline or built a published benchmark.
- Write clearly, including evaluation reports a founder can act on.
- No degree requirement.
Responsibilities
- Own the context layer, managing system context, retrieval, and memory as one budget.
- Define contracts, results, and failure modes for tools called by Mimo.
- Build offline evaluation suites, graded live passes, and regression gates for behavior changes.
- Shape how Mimo reasons, asks, explains, and recovers.
- Define rules users can set for their own Mimo.
- Decide which model runs where and what gate a new model must pass before shipping.
View Full Description & ApplyYou'll be redirected to the employer's site
