AI Safety & Evaluations Engineer (End-to-End)

TTN Talent; San Francisco (CA); On-site; USD 200,000 - 400,000; Full time

Job summary

TTN Talent in San Francisco is seeking a hands-on software engineer passionate about AI alignment, safety, and security. You will own technical projects end to end, from idea through implementation, testing and refinement.

You will build environments and evaluation tasks to identify misaligned or unreliable model behavior, and improve tooling to isolate, measure, and refine those behaviors. Salary on offer is $200,000 to $400,000.

Qualifications

• Strong hands-on software engineering experience with focus on AI alignment, safety or security.
• Experience with Python, agent tooling, evals, RL environments or similar technical infrastructure.
• Ability to independently own technical projects end to end, from idea through implementation, testing and refinement.

Responsibilities

• Build environments and evaluation tasks to identify misaligned or unreliable model behaviour, and improve software used to isolate, measure and refine those behaviours.

Job description

TTN Talent in San Francisco is seeking a hands-on software engineer passionate about AI alignment, safety, and security. You will own technical projects end to end, from idea through implementation, testing and refinement.

You will build environments and evaluation tasks to identify misaligned or unreliable model behavior, and improve tooling to isolate, measure, and refine those behaviors. Salary on offer is $200,000 to $400,000.