AI Safety & Agent Robustness Research Scientist

JRNLClub

New York (NY)

On-site

USD 216,000 - 270,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Scale Labs, a research arm of Scale AI, is seeking a Research Scientist focused on Agent Robustness. You will investigate AI agent safety, design evaluation harnesses, and explore mitigation strategies for advanced agent capabilities.

The role emphasizes cross-functional collaboration across research, engineering, and policy interfaces to advance safe AI deployments. The position targets seasoned ML researchers with a track record in publishing and practical experience turning theories into

Qualifications

  • Proven track record in ML research, ideally in generative AI.
  • Experience collaborating across teams to turn research into prototypes.
  • Experience with post-training and RL techniques such as RLHF, DPO, GRPO.
  • Strong written and verbal communication to operate in cross-functional teams.
  • At least three years addressing sophisticated ML problems, in research or product development.

Responsibilities

  • Research AI agent capabilities focusing on safety, risk factors, and benchmarking methodologies.
  • Design and build evaluation harnesses to test agents under challenging conditions.
  • Develop exploits and mitigations for failure modes as agents gain new capabilities.
  • Characterize risks in multi-agent systems and design mitigations.

Skills

Agent robustness
RL techniques
ML research publications
Cross-functional collaboration
Technical research execution

Tools

SWE-bench
WebArena
OSWorld
Inspect

Job description

Scale Labs, a research arm of Scale AI, is seeking a Research Scientist focused on Agent Robustness. You will investigate AI agent safety, design evaluation harnesses, and explore mitigation strategies for advanced agent capabilities.

The role emphasizes cross-functional collaboration across research, engineering, and policy interfaces to advance safe AI deployments. The position targets seasoned ML researchers with a track record in publishing and practical experience turning theories into

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Scientist, Agent Robustness
Research Scientist, Agent Robustness

Ai Safety • New York (NY)

On-site
USD 216,000 - 270,000
Health insurance
Dental coverage
Vision coverage
+1
Research Scientist, Agent Robustness
Research Scientist, Agent Robustness

JRNLClub • New York (NY)

On-site
USD 216,000 - 270,000
AI Agent Engineer — Scale Safe, Smart Agents
AI Agent Engineer — Scale Safe, Smart Agents

TRM Labs • United States

Hybrid
USD 200,000 - 275,000
Equity plan
AI Safety & Oversight Researcher
AI Safety & Oversight Researcher

Society for AI Security • San Francisco (CA)

Hybrid
USD 150,000 - 240,000
Senior AI Agent Research Scientist
Senior AI Agent Research Scientist

The Institute for Performance and Learning • San Francisco (CA), New York (NY), Seattle (WA)

On-site
CAD 370,000 - 463,000
Health, dental and vision coverage
Retirement benefits
Learning and development stipend
+2
Remote AI Research Scientist - Reliable Agent Systems
Remote AI Research Scientist - Reliable Agent Systems

Not Specified • United States

Remote
USD 130,000 - 200,000
AI Agent Engineer - Build Safe, Scalable Agent Systems
AI Agent Engineer - Build Safe, Scalable Agent Systems

FDE Times • United States

Remote
USD 200,000 - 275,000
Equity plan
AI Safety & Systems Researcher
AI Safety & Systems Researcher

Precision Labs • San Francisco (CA)

Hybrid
USD 170,000 - 250,000
Research Scientist: Safer Frontiers in Agent RL & AI Safety
Research Scientist: Safer Frontiers in Agent RL & AI Safety

ByteDance • San Jose (CA)

On-site
USD 254,000 - 588,000
Health insurance
401(k) with company match
Paid parental leave
+1
RL Research Engineer — Scalable, Safe AI Systems
RL Research Engineer — Scalable, Safe AI Systems

Anthropic Limited • San Francisco (CA)

Hybrid
USD 500,000 - 850,000
Equity donation matching
Generous vacation & parental leave
Flexible working hours
+1