Senior Applied Scientist — Self-Improving RL Pipelines

Hippocratic AI Inc.; Seattle (WA); On-site; USD 180,000 - 280,000; Full time

Job summary

Hippocratic AI is seeking an engineering-focused ML professional to build the training, evaluation, and deployment loops for a self-improving system. You will design reward signals, mitigate reward hacking, and ensure safe, reliable feedback loops.

You will own data pipelines, run continual learning or RLHF/RLAIF related workflows, and collaborate with research and product to ship robust, safe systems.

Qualifications

• Excellent Python and clean, well-tested ML training code.

Responsibilities

• Build and maintain training, evaluation, and deployment loops for the self-improvement system.
• Design and implement reward and feedback signals; mitigate reward hacking and distribution drift.
• Build evaluation harnesses and metrics for model safety and quality.
• Own data pipelines and automated data flywheels feeding the learning loop.
• Debug subtle model-quality regressions and stabilize training loops.
• Collaborate with research and product to ship robust, safe systems.

Skills

Python

ML training code

data pipelines

distributed / large-scale training

experiment tracking

debugging model degradation

reinforcement learning

reward modeling

RLHF / RLAIF pipelines

agentic evaluation harnesses

Education

PhD or MS in RL/ML

Job description

Hippocratic AI is seeking an engineering-focused ML professional to build the training, evaluation, and deployment loops for a self-improving system. You will design reward signals, mitigate reward hacking, and ensure safe, reliable feedback loops.

You will own data pipelines, run continual learning or RLHF/RLAIF related workflows, and collaborate with research and product to ship robust, safe systems.