AI Simulation & Evaluation Engineer — Onsite SF (Equity)

raydar; San Francisco (CA); On-site; USD 150,000 - 300,000; Full time

Job summary

Raydar in San Francisco, CA is seeking a Machine Learning Engineer to design and build realistic simulated work environments and evaluation tasks used to train AI models.

You will develop synthetic workplace data, design robust graders and benchmarks, and translate feedback into new test cases. This is an early-career role requiring a strong interest in RL and model post-training, with on-site work in San Francisco.

Qualifications

• 0 to 3 years of experience in ML or related field.
• A degree from a top-30 school.
• Background in post-training or reinforcement learning, from research or industry.
• A good sense of what makes a simulated environment rich, detailed and believable.
• The ability to spot how a model might game an environment or grader, and to fix it.

Responsibilities

• Build simulated environments with generated records, files and communications that behave like real workplaces.
• Design graders and scoring functions that resist exploitation by models.
• Create benchmarks whose rankings track real-world performance.
• Convert user feedback and corrections into evaluation tasks.
• Take over environment and benchmark work currently led by the founders.

Skills

Reinforcement learning

Simulated environments

Evaluation design

Environment risk spotting

Education

Degree from a top-30 school

Job description

Raydar in San Francisco, CA is seeking a Machine Learning Engineer to design and build realistic simulated work environments and evaluation tasks used to train AI models.

You will develop synthetic workplace data, design robust graders and benchmarks, and translate feedback into new test cases. This is an early-career role requiring a strong interest in RL and model post-training, with on-site work in San Francisco.