Member of Technical Staff, AI Researcher (New Stealth Startup)
Core
Design evaluation frameworks, benchmarks, and feedback systems for frontier AI models (LLMs, agents, RL) to measure behavior and improve alignment.
Role type
Senior IC AI Researcher (Research & Engineering)
Builds
Evaluation frameworks, reward models, programmatic verifiers, RL environments, and production-quality data systems.
Domain
Artificial Intelligence / Frontier Models / Reinforcement Learning
Deliverable
production ML models
Required skills
Python, AI agents, reinforcement learning, model evaluation, reward modeling, experimental design, data attribution, software engineering
Preferred skills
Advanced degree in ML/AI/CS, published research, open-source contributions
Technologies
Python, LLMs, RL environments, automated verifiers
Responsibilities
Design and build evaluation frameworks and benchmarks for frontier AI models; Develop reward models and feedback systems; Design and run supervised fine-tuning and RL experiments; Build systems for producing high-quality human data; Translate research questions into rigorous experiments; Prototype and convert findings into production systems.
Seniority
Senior, hands-on IC
