Founding RL Engineer: Shape Core AI Systems

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

Job summary

Clera in San Francisco, CA is building core reinforcement learning systems as a founding engineer on an early-stage AI team. You will work directly with the founders and own the process from environment design and model training through evaluation.

You design RL environments, train models with PPO, GRPO, DPO, RLHF, and RLAIF, and develop evaluation frameworks. You will run experiments, interpret results, and decide what approaches to explore next, scaling training on GPU clusters.

Qualifications

• 2+ years hands-on RL or ML engineering (could range 2–10+ years).
• Strong Python and deep experience with PyTorch or JAX.
• Experience training models with reinforcement learning (policy gradients, reward modeling, RLHF).

Responsibilities

• Design and build RL environments, reward functions, and training pipelines.
• Train and fine-tune models using PPO, GRPO, DPO, RLHF, and RLAIF.
• Develop evaluation frameworks to measure model and agent performance.
• Run experiments, interpret results, and decide next exploration steps.
• Scale training on GPU clusters and maintain reliable pipelines.
• Turn research ideas into production systems.
• Help establish engineering culture and hire future engineers.

Skills

Python

Reinforcement learning

Distributed training

Education

Bachelor in CS / Math / Physics

Tools

PyTorch

JAX

Ray

CUDA

Kubernetes

Gymnasium

RLlib

MuJoCo

TRL

verl

OpenRLHF

Job description

Clera in San Francisco, CA is building core reinforcement learning systems as a founding engineer on an early-stage AI team. You will work directly with the founders and own the process from environment design and model training through evaluation.

You design RL environments, train models with PPO, GRPO, DPO, RLHF, and RLAIF, and develop evaluation frameworks. You will run experiments, interpret results, and decide what approaches to explore next, scaling training on GPU clusters.