Member of Technical Staff - ML Research

What you'll do

• Co-design and implement reinforcement learning environments, algorithms, reward models, and reward-signal experiments.
• Build, scale, and improve model fine-tuning, evaluation, and test-time optimization pipelines.
• Collaborate with research teams to productionize emerging techniques and debug training pipelines and model behavior.

What they ask for

• Deep expertise in reinforcement learning and post-training, with a track record of deploying models from research into real-world use.
• Experience building end-to-end ML pipelines and using RL and fine-tuning for LLMs and code models on reasoning, tool-use, and structured coding tasks.
• Strong software engineering skills and experience with complex ML systems, large-scale distributed systems, high-performance computing, and distributed training frameworks.
• Ability to analyze and debug training, and to prototype, benchmark, and productionize reliable training pipelines.

Nice to have

• Post-training work at a frontier lab; publications in top ML or EDA venues; or experience as a founding ML engineer/researcher or early hire at an AI deeptech startup.
• Background in electrical/computer engineering, computer architecture, or chip-design and verification processes.

Tools

PyTorch, CUDA, QLoRA, ZeRO

AI focus

Research and train AI models for chip design, verification, and exploration, including reinforcement learning, reward modeling, fine-tuning, evaluation, and test-time optimization.