Founding RL Engineer: Build Scalable AI Agents

Clera; San Francisco (CA); On-site; USD 125,000 - 200,000; Full time

Job summary

Clera in San Francisco, CA seeks a Founding Reinforcement Learning Engineer to build core systems for training and evaluating AI agents. You will own from environment design through model evaluation and help shape the team's technical direction.

You will design RL environments, train models with policy gradient methods, and scale pipelines across GPU clusters. Visa sponsorship is available for this on-site role in San Francisco, United States.

Qualifications

• Minimum 2 years hands-on experience in reinforcement learning or ML engineering.
• Strong Python skills with PyTorch or JAX experience.
• Practical experience training models with policy gradient methods and RLHF.
• Experience with distributed training, GPU infra, RL environments, and evaluation.
• Record of turning research ideas into production systems.
• Degree in CS, math, physics, or related field; graduate study a plus.
• Experience with LLM post-training or RL training libraries is a plus.

Responsibilities

• Design and build RL environments, reward functions, and training pipelines.
• Train and fine-tune models using PPO, GRPO, DPO, RLHF, and RLAIF.
• Build evaluation frameworks to measure model and agent performance.
• Run experiments, analyze results, and guide research priorities.
• Scale training across GPU clusters and maintain pipelines.
• Bring research ideas into production systems and establish engineering practices.
• Contribute to hiring as the engineering team grows.

Skills

Reinforcement learning

Python

PyTorch

JAX

Policy gradient

RLHF

Distributed training

GPU infrastructure

Model evaluation

Production systems

Education

Bachelor's degree in CS/Math/Physics

Job description

Clera in San Francisco, CA seeks a Founding Reinforcement Learning Engineer to build core systems for training and evaluating AI agents. You will own from environment design through model evaluation and help shape the team's technical direction.

You will design RL environments, train models with policy gradient methods, and scale pipelines across GPU clusters. Visa sponsorship is available for this on-site role in San Francisco, United States.