Data Engineer
Core
Building RL environments and task creation infrastructure for agent training, including designing observation/action spaces, reward signals, and success criteria.
Role type
Senior Data Engineer (RL Environments)
Builds
Novel RL environments and training infrastructure for digital world agents
Domain
AI Research / Reinforcement Learning
Deliverable
production ML models
Required skills
Python (numpy, pandas, Parquet, HDF5), Data Engineering (pipelines, ETL, data modeling), RL Frameworks (Gymnasium, OpenAI Gym, dm_env), Data Versioning (DVC, MLflow, W&B), Cloud Infrastructure (AWS, GCP), Docker, ML Storage Formats
Technologies
Gymnasium, OpenAI Gym, dm_env, DVC, MLflow, W&B, Docker, AWS, GCP, Parquet, HDF5, JSON Lines
Responsibilities
Design observation spaces, action spaces, reward signals, and success criteria for new RL environments; Build infrastructure enabling world-scale RL training; Collaborate with research teams on RL environment and task creation
Seniority
Senior, hands-on IC