Sr. Model Engineer, Post-Training & RL
Core
Developing post-training and reinforcement learning techniques for large AI models to improve reasoning, truthfulness, and real-world capabilities.
Role type
Senior IC machine-learning engineer (post-training & RL)
Builds
Production-grade AI models (Grok stack) and alignment methods
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
Python, PyTorch, JAX, Rust, C++, large model training (1B+ parameters), reward modeling, preference optimization (RLHF/DPO), reinforcement learning
Preferred skills
truth-seeking AI focus, post-training/RLHF experience, power user of AI models
Technologies
Python, PyTorch, JAX, Rust, C++, Grok models, Colossus supercomputers
Responsibilities
Implement reward modeling and preference optimization algorithms, develop RL strategies for model improvement, train large-scale neural networks, push boundaries of alignment methods
