AI Alignment Research Scientist

OpenAI, Inc.

San Francisco (CA)

Hybrid

GBP 90,000 - 120,000

Full time

12 days ago

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

OpenAI, Inc. is seeking Research Engineers/Researchers to advance alignment research, designing scalable experiments that ensure AI systems reliably follow human intent while remaining safe and trustworthy.

You will collaborate across teams to develop evaluations, tools, and interfaces that study model robustness and alignment in complex scenarios. The role may be based in London or San Francisco, requiring strong engineering skills, knowledge of large-scale ML (e.g., PyTorch), and the ability

Qualifications

  • Have a PhD or equivalent experience in research in computer science, computational science, data science, cognitive science, or similar fields.
  • Strong engineering skills, particularly in designing and optimizing large-scale machine learning systems (e.g., PyTorch).
  • Can develop data visualization or data collection interfaces (e.g., TypeScript, Python).
  • Enjoy fast-paced, collaborative, and cutting-edge research environments.
  • Want to focus on developing AI models that are trustworthy, safe, and reliable, especially in high-stakes scenarios.

Responsibilities

  • Develop and evaluate alignment capabilities that are subjective, context-dependent, and hard to measure.
  • Design evaluations to reliably measure risks and alignment with human intent and values.
  • Build tools and evaluations to study and test model robustness in different situations.
  • Design experiments to understand laws for how alignment scales as a function of compute, data, lengths of context and action, as well as resources of adversaries.
  • Design and evaluate new Human-AI-interaction paradigms and scalable oversight methods that redefine how humans interact with, understand, and supervise our models.
  • Train model to be calibrated on correctness and risk.
  • Designing novel approaches for using AI in alignment research

Skills

Team collaboration
Experiment design
Research in AI alignment
Strong engineering mindset

Education

PhD or equivalent in CS/related fields

Tools

PyTorch
TypeScript
Python

Job description

OpenAI, Inc. is seeking Research Engineers/Researchers to advance alignment research, designing scalable experiments that ensure AI systems reliably follow human intent while remaining safe and trustworthy.

You will collaborate across teams to develop evaluations, tools, and interfaces that study model robustness and alignment in complex scenarios. The role may be based in London or San Francisco, requiring strong engineering skills, knowledge of large-scale ML (e.g., PyTorch), and the ability

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Engineer — AI Alignment & Safety | Equity & PTO
Research Engineer — AI Alignment & Safety | Equity & PTO

Best AI Tools Wiki • San Francisco (CA)

Hybrid
USD 180,000 - 240,000
Equity package
Unlimited PTO
Free meals
Researcher, Alignment
Researcher, Alignment

OpenAI, Inc. • San Francisco (CA)

Hybrid
GBP 90,000 - 120,000
Research Engineer: AI Safety & Alignment
Research Engineer: AI Safety & Alignment

Anthropic Limited • San Francisco (CA)

Hybrid
USD 350,000 - 500,000
Competitive compensation
Generous vacation and parental leave
Flexible working hours
Research Engineer — Alignment
Research Engineer — Alignment

Best AI Tools Wiki • San Francisco (CA)

Hybrid
USD 180,000 - 240,000
Equity package
Unlimited PTO
Free meals
AI Alignment Researcher — Human-Centric & Robustness
AI Alignment Researcher — Human-Centric & Robustness

Safety Talent Limited • San Francisco (CA)

On-site
USD 120,000 - 180,000
AI Safety & Alignment Research Scientist (GenAI)
AI Safety & Alignment Research Scientist (GenAI)

DeepMind Technologies Limited • Mountain View (CA)

Hybrid
USD 207,000 - 300,000
Researcher, Alignment & Mechanistic Interpretability
Researcher, Alignment & Mechanistic Interpretability

Rebash • San Francisco (CA)

On-site
USD 150,000 - 210,000
Researcher, Alignment Interpretability
Researcher, Alignment Interpretability

Society for AI Security • United States

On-site
USD 160,000 - 230,000
Research Scientist — AI Safety & Alignment (Remote)
Research Scientist — AI Safety & Alignment (Remote)

Aisafety • Berkeley (CA)

Hybrid
USD 120,000 - 190,000
Catered lunch and dinner
Visa sponsorship for in-person employees
Reimbursement for work-related travel
Alignment Scientist/Engineer
Alignment Scientist/Engineer

AE Studio • United States

Remote
USD 180,000 - 240,000
Remote-first
Coworking spaces
Health insurance
+5