AI Engineer

Momentic builds an AI-native software testing platform for engineering teams. The AI Engineer will improve the models and agents behind the platform by fine-tuning models, developing datasets and evaluations, and making production agents more reliable and efficient.

Responsibilities:

• Fine-tune models for long-running agents, including agents that investigate whether test failures come from infrastructure, recent code changes, or test authorship
• Build and curate training and evaluation datasets from production workflows, using failure patterns to identify opportunities for improvement
• Develop LLM evaluations and observability that connect offline results with production behavior and help the team verify improvements
• Tune prompts, context, and model behavior to improve task success, reliability, latency, token usage, and cost
• Design repeatable experiments and help publish benchmarks that demonstrate our core agents’ performance on testing and browser workflows
• Own technical projects from problem definition through delivery, working with the engineering team to make practical tradeoffs and ship improvements