Founding Member of Technical Staff - Post Training

What You'll Do

• Co-design and implement Reinforcement Learning environments and algorithms, Reward Models, and reward signal experiments.
• Work at the intersection of cutting-edge research and production engineering for chip designs, implementing, scaling, and improving post-training techniques to enhance model capabilities and usability.
• Design, build, and run robust, efficient pipelines for model fine-tuning and evaluation, ensuring that theoretical performance translates into production-ready implementations.
• Own the end-to-end RL workflow—from reward modeling and environment design to test-time optimization and scaling.
• Collaborate with research teams to translate emerging techniques into production-ready implementations and debug complex issues in training pipelines and model behavior.

Qualifications & Skills

• PhD in Computer Science, EECS, Mathematics, or a closely related field, with specialization in Machine Learning, Deep Learning, or Artificial Intelligence.
• Strong industry or research background building end-to-end ML pipelines, with experience in RL and fine-tuning LLMs and code models for reasoning, tool use, and structured coding tasks.
• Strong software engineering skills with experience building complex ML systems, comfortable with large-scale distributed systems, high-performance computing, and distributed training frameworks (e.g., PyTorch, CUDA, QLoRA, ZeRO).
• Adept at analyzing and debugging model training processes, capable of balancing research exploration with engineering rigor and operational reliability.
• Fast-moving builder who can prototype, benchmark, and productionize training pipelines with tight feedback loops.
• Experience as a Founding ML Engineer/Researcher or early hire at an AI deeptech startup.