About the role
About the Role
Join an early-stage AI team building reinforcement learning systems from the ground up. You will own the end-to-end process, from environment design and model training to evaluation, helping shape the technical direction and engineering culture.
What You'll Do
* Design and build reinforcement learning environments, reward functions, and training pipelines.
* Train and fine-tune models using methods such as PPO, GRPO, DPO, RLHF, and RLAIF.
* Develop evaluation frameworks to measure model and agent performance.
* Run experiments, interpret results, and decide what to explore next.
* Scale training on GPU clusters and keep training pipelines reliable.
* Turn research ideas into production systems.
* Help establish engineering practices and hire future team members.
What We're Looking For
* At least 2 years of hands-on experience in reinforcement learning or machine learning engineering.
* Strong Python skills and deep experience with PyTorch or JAX.
* Practical experience training models with reinforcement learning methods, including policy gradients, reward modeling, or RLHF.
* Experience with distributed training, GPU infrastructure, RL environments, reward functions, training pipelines, and model or agent evaluation.
* A track record of taking research ideas into production systems.
* A degree in computer science, mathematics, physics, or a related field; a master's or PhD is a plus.
* LLM post-training or agent training experience is beneficial, as are RL publications or open-source work and experience with simulation frameworks or training libraries.
Compensation & Benefits
Base salary: $125,000 to $200,000 USD annually. Visa sponsorship is available.
Location
On-site in San Francisco, California, United States. Candidates must be based in or willing to relocate to San Francisco.