Senior AI Domain Expert - GenAI & Engineering QA

Obsidian; San Francisco (CA); Hybrid; USD 150,000 - 230,000; Full time

Job summary

Obsidian seeks a senior engineering and software domain expert to join a leading AI lab's research and program management teams in the Bay Area. You will work on how frontier AI models reason about real engineering and software development work, reviewing and defining high-quality outputs for production-grade systems.

You will write instruction specs, create golden solutions, and build robust benchmarks while aligning with clients and researchers.

Qualifications

• Bachelor's degree or higher in computer science, software engineering, or a closely related field; MS/PhD preferred.
• 4+ years of substantive professional engineering practice shipping production software or engineered systems.
• Genuine domain depth in areas like distributed systems, security/cryptography, ML systems, or platform engineering.
• Clear progression to senior roles with ownership of systems and design decisions.
• Hands-on use of large language models in professional work (AI fluency).
• Ability to commit to 40 hours/week for 6 months.

Responsibilities

• Vet the quality of engineering knowledge work tasks and model outputs, identifying deep issues and edge cases.
• Write instruction specs and golden datasets for engineering problems and define new tasks.
• Design challenging engineering tasks and evaluation sets to advance domain depth.
• Translate tacit engineering judgment into explicit, teachable criteria with stakeholders.

Skills

AI fluency

4+ years experience

Senior-level ownership

Written feedback

On-site collaboration

Education

Bachelor's degree or higher in CS/engineering

Job description

Obsidian seeks a senior engineering and software domain expert to join a leading AI lab's research and program management teams in the Bay Area. You will work on how frontier AI models reason about real engineering and software development work, reviewing and defining high-quality outputs for production-grade systems.

You will write instruction specs, create golden solutions, and build robust benchmarks while aligning with clients and researchers.