Responsibilities
- Construct and refine foundational research systems including evaluation frameworks, agent workflows, hallucination detection mechanisms, coding assessment benchmarks, and pipelines connecting research to production.
- Architect, develop, and scale autonomous agent systems across backend services, frontend interfaces, and machine learning model integrations, working closely with research teams and leadership.
- Take full ownership of agent system reliability, monitoring capabilities, and performance metrics, including logging, distributed tracing, instrumentation, and safety validations.
- Deliver production-ready features validated by research within one week, managing the full development lifecycle independently.
- Create reusable tools, software development kits, and internal platforms that enhance development speed for Research, Quality Assurance, and Engineering teams.
Compensation
Competitive salary and equity package
Work Arrangement
Remote with flexible hours
Team
Small, fast-moving team focused on AI research and product development
Available for qualified candidates
