Founding RL Engineer

Clera

San Francisco, CA

On-site

Who this role is best for

Best suited to reinforcement learning engineers with hands-on experience in building environments and training pipelines, working in early-stage AI startups in San Francisco.

Best fit for

Candidates with 2+ years of RL experience and a background in deploying research into production systems
— “A track record of bringing research ideas into production”
Individuals with deep Python and PyTorch/JAX expertise and experience in distributed training
— “Strong Python skills and deep experience with PyTorch or JAX”
Engineers who have worked with reward modeling, policy gradients, or RLHF in prior projects
— “Practical experience training models with reinforcement learning methods, including policy gradients, reward modeling, or RLHF”

Things to consider

On-site requirement in San Francisco may pose logistical challenges for non-local candidates
— “This is an on-site role based in San Francisco, California, United States”
The role demands full ownership of training and evaluation processes, not just execution
— “You will own the full loop from environment design through training and evaluation”

How to stand out

Highlight experience in creating end-to-end RL environments and reward systems in your resume
— “Design and build reinforcement learning environments, reward functions, and training pipelines”
Emphasize your hands-on work with PPO, GRPO, DPO, RLHF, or RLAIF methods in your interview narrative
— “Train and fine-tune models using methods such as PPO, GRPO, DPO, RLHF, and RLAIF”
Demonstrate your ability to scale training on GPU clusters and maintain training pipelines
— “Scale training on GPU clusters and maintain reliable training pipelines”
Showcase your experience turning research into production systems, especially in AI or machine learning contexts
— “Turn research ideas into production systems and help establish engineering practices”
Demonstrate practical knowledge of RL environments, reward functions, and training pipelines in your application materials
— “Experience with RL environments, reward functions, training pipelines, and evaluation frameworks”

Pace · Fast PacedCollaboration · HighAutonomy · MediumDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

Design and build reinforcement learning environments
Train and fine-tune models using reinforcement learning methods

Typical background

2+ years of hands-on experience in reinforcement learning or machine learning engineering

Skills & requirements

Required

Reinforcement LearningPythonPyTorchDistributed TrainingGPU Clusters

Preferred

LLM Post-trainingSimulation Frameworks

Stack & domain

Reinforcement LearningMachine Learning EngineeringPythonPyTorchJAXPPOGRPODPORLHFRlaifDistributed TrainingGPU InfrastructureLLM Post-trainingAgent TrainingSimulation FrameworksTraining Libraries

About the role

Original posting from Clera via Ashby

ABOUT THE ROLE
Join an early-stage AI team building reinforcement learning systems to help AI agents handle complex work. You will own the full loop from environment design through training and evaluation, while helping shape the team's technical direction.
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.
Build evaluation frameworks to measure model and agent performance.
Run experiments, interpret results, and use findings to guide what to try next.
Scale training on GPU clusters and maintain reliable training pipelines.
Turn research ideas into production systems and help establish engineering practices.
Contribute to hiring as the engineering team grows.
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 evaluation frameworks.
A track record of bringing research ideas into production, plus a degree in computer science, mathematics, physics, or a related field.
Experience with LLM post-training, agent training, simulation frameworks, or training libraries is a plus.
COMPENSATION & BENEFITS
Compensation is $125,000 to $200,000 USD annually. Visa sponsorship is available.
LOCATION
This is an on-site role based in San Francisco, California, United States.

Source: Clera careers (Ashby)