FREE ACCESS
5,000–10,000 jobs/day
See all jobs on Scoutfield
Search thousands of fresh jobs every day.
Discover
- Fresh listings
- Fast filters
- No subscription required
Create a free account and start exploring right away.
About the role
Key responsibilities & impact- Build features for understanding traces, evaluating agent behavior, and turning evaluation results into improvements
- Run experiments on Mastra’s primitives
- Investigate where primitives perform well and where they fall short
- Improve primitive configuration and behavior based on findings
- Turn evaluation work into capabilities developers can use in their applications
- Work on features including trace intelligence, agent learning, autoevaluations, suggestions, and rollouts
Requirements
What you’ll need- Shipped agents and agentic applications into production
- Tuned and tweaked agents to improve accuracy
- Ability to benchmark results against existing datasets or intelligently create datasets
- Hands-on engineering experience spanning experiments, benchmarks, and product code
Benefits
Comp & perks- Fully remote work
- Work across North American and European time zones