🛠 Tech Stack

💼 About This Role

You'll build and scale automated evaluation pipelines for clinical-grade AI agents at a healthcare startup. Your work will define benchmarks and deploy CI gates for accuracy and safety. This role offers first-of-their-kind problems at the intersection of AI and medicine.

🎯 What You'll Do

• Design and implement LLM-as-judge evaluation pipelines
• Define clinical-grade benchmarks for agentic tasks
• Build automated CI gates for accuracy and safety
• Partner with engineering to land evaluation frameworks

📋 Requirements

• Python and ML background with PyTorch/TensorFlow
• Experience with LLM evaluation and benchmarking
• Track record of published research or deep applied work in LLMs

✨ Nice to Have

• Experience with healthcare or clinical NLP
• Familiarity with LangChain or LlamaIndex
• Strong communication and technical writing skills

🎁 Benefits & Perks

• 🧠 High-impact work on first-of-their-kind problems
• ⚡️ Autonomy and ownership with urgent execution
• ❤️ Direct impact on doctor efficiency and patient care

🚩 Heads Up

• No salary mentioned in listing