Founding Reinforcement Learning Engineer

Job overview

The Founding Reinforcement Learning Engineer role is onsite in San Francisco, CA. Compensation is $125,000–$200,000 per year. Clera is an early-stage AI team building systems for training and evaluating AI agents. The engineer owns work from environment design through model training and evaluation, helping shape the team’s technical direction. The role turns research ideas into production systems and establishes engineering practices as the team grows.

What you'll do

• Design reinforcement-learning environments, reward functions, and training pipelines
• train and fine-tune models using PPO, GRPO, DPO, RLHF, and RLAIF
• build model and agent evaluation frameworks
• run experiments and analyze results
• scale training across GPU clusters
• maintain reliable pipelines
• bring research into production systems
• contribute to hiring as the engineering team grows.

What we're looking for

Skills & competencies

founding reinforcement learning engineer

clera

san francisco ca

onsite

artificial intelligence

reinforcement learning

python

pytorch

jax

rlhf

gpu clusters

model evaluation

$125k–$200k/year

visa sponsorship available

Work arrangement

• Weekend coverage required

Why this role

Visa sponsorship is available. Experience with LLM post-training, agent training, simulation frameworks, or reinforcement-learning libraries is a plus.

About the employer

Clera is hiring for this role. Industry: Custom Computer Programming Services. Sector: 54.