Sepal AI teams with frontier research labs to probe whether AI agents actually achieve the goals humans set - safely, securely, and repeatably. We’re hiring a Software Engineer (DevOps + Python) to automate large-scale evaluations LLM workflows.
About the role
Sepal AI teams with frontier research labs to probe whether AI agents actually achieve the goals humans set - safely, securely, and repeatably. We’re hiring a Software Engineer (DevOps + Python) to automate large-scale evaluations LLM workflows.
🧠 What You'll Do
- Build and maintain Python scripts & CI pipelines for AI doing complex tasks.
- Extend our internal evaluation framework to capture success/failure signals and edge-case logs.
- Collaborate with research teams to plug in new LLM agents, datasets, and scoring rubrics.
✅ Who You Are
- 3+ years writing production Python and automating infra (Docker, Kubernetes, Terraform, or similar).
- Able to translate vague research specs into clean, testable engineering artifacts.
- Bonus: experience with MCP-style eval tooling, RLHF/LLM agent frameworks, or benchmark design.
💸 Pay: $30–45/hr
🌍 Remote
⏱ Flexible hours (async, milestone-based)
Official source: expert-hub.sepalai.com. Details can change; the platform's page is the final word. How we check listings.
