Research Engineer — AI Alignment & Safety | Equity & PTO

Best AI Tools Wiki; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity package

Unlimited PTO

Free meals

Job summary

OpenAI is seeking a Research Engineer to work on superalignment — developing techniques to align AI systems that may become more capable than humans. You will build evaluation systems, develop alignment techniques, and work at the frontier of AI safety.

Strong implementation skills in Python and PyTorch, plus 4+ years of ML or research engineering experience, are expected. Experience with large-scale model training and understanding alignment concepts are valued.

Qualifications

• 4+ years of ML engineering or research engineering
• Strong Python and PyTorch implementation skills
• Understanding of alignment concepts and challenges
• Experience with large-scale model training
• Publications in AI safety or alignment; experience with interpretability tools
• Background in formal methods or verification; familiarity with scalable oversight techniques

Responsibilities

• Build evaluation systems to assess alignment
• Develop alignment techniques for superalignment
• Work at the frontier of AI safety

Job description

OpenAI is seeking a Research Engineer to work on superalignment — developing techniques to align AI systems that may become more capable than humans. You will build evaluation systems, develop alignment techniques, and work at the frontier of AI safety.

Strong implementation skills in Python and PyTorch, plus 4+ years of ML or research engineering experience, are expected. Experience with large-scale model training and understanding alignment concepts are valued.