Research Engineer, Alignment & Model Safety — SF Onsite

Mechanize

San Francisco (CA)

On-site

USD 300,000 - 400,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Mechanize in San Francisco is seeking a research engineer to create evals that test for misaligned model behaviors. The role focuses on assessing when models go off the rails, such as acting sycophantically, being dishonest, or proposing unsafe actions.

This in-person position offers a generous compensation package with equity and a bonus, reflecting the seniority of the work and the emphasis on robust evaluation methodologies.

Qualifications

  • Create evals that test for misaligned model behaviors.

Responsibilities

  • Develop evals to test misalignment in model behavior.

Job description

Mechanize in San Francisco is seeking a research engineer to create evals that test for misaligned model behaviors. The role focuses on assessing when models go off the rails, such as acting sycophantically, being dishonest, or proposing unsafe actions.

This in-person position offers a generous compensation package with equity and a bonus, reflecting the seniority of the work and the emphasis on robust evaluation methodologies.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Model-Behavior Research Engineer: Evals & Alignment
Model-Behavior Research Engineer: Evals & Alignment

OpenAI • San Francisco (CA)

On-site
USD 310,000 - 460,000
Equity offers
AI Safety Researcher — Investigate Model Behavior & Impact
AI Safety Researcher — Investigate Model Behavior & Impact

Typesafe AI, Inc. • San Francisco (CA)

On-site
USD 180,000 - 240,000
Research Engineer: AI Safety & Alignment
Research Engineer: AI Safety & Alignment

Anthropic • San Francisco (CA)

Hybrid
USD 350,000 - 500,000
Competitive compensation
Generous vacation and parental leave
Flexible working hours
Hybrid Frontier AI Safety Researcher
Hybrid Frontier AI Safety Researcher

Precision Labs • San Francisco (CA)

Hybrid
USD 180,000 - 240,000
Relocation assistance
AI Simulation & Evaluation Engineer — Onsite SF (Equity)
AI Simulation & Evaluation Engineer — Onsite SF (Equity)

raydar • San Francisco (CA)

On-site
USD 150,000 - 300,000
Frontier-Model Safety Researcher & Evaluations
Frontier-Model Safety Researcher & Evaluations

OpenAI • San Francisco (CA)

Hybrid
USD 380,000 - 500,000
Relocation assistance
Hybrid work model
Researcher, Chain-of-Thought Monitorability & Alignment
Researcher, Chain-of-Thought Monitorability & Alignment

OpenAI • San Francisco (CA)

Hybrid
USD 120,000 - 150,000
Relocation assistance
Hybrid work model
Frontier AI Misalignment Monitoring Lead & Researcher
Frontier AI Misalignment Monitoring Lead & Researcher

Applied Methods Ltd • San Francisco (CA)

On-site
USD 38,000 - 50,000
Researcher, Agent Safety, Training and Evaluations
Researcher, Agent Safety, Training and Evaluations

OpenAI • San Francisco (CA)

Hybrid
USD 380,000 - 500,000
Relocation assistance
Hybrid work model
Research Engineer / Research Scientist - Model Behavior at OpenAI San Francisco, CA
Research Engineer / Research Scientist - Model Behavior at OpenAI San Francisco, CA

OpenAI • San Francisco (CA)

On-site
USD 310,000 - 460,000
Equity offers