Member of Technical Staff - Research, AI Safety

Vals AI • San Francisco, CA

16h • $130,000 - $185,000 • Onsite

About The Position

Vals AI is seeking an exceptional researcher to design and build next-generation AI benchmarks for identifying misaligned behavior in frontier models and agents, such as reward hacking, scheming, deception, loss of control, and multi-agent safety risks. The role involves leading development of novel benchmarks and evaluation infrastructure that assess misalignment risks in large language models and help shape how foundation models and generative AI applications are developed. The work is intended to define standards for evaluating real-world tasks and directly influence how AI systems are assessed.

Requirements

• Substantial, hands-on experience in safety evaluations, monitorability, scheming, deception, or multi-agent safety.
• Understanding of neural networks and the fundamentals of model training.
• Excellent coding skills and ability to design and build complex evaluation environments, mostly in Python.
• Ability to clearly communicate complex research ideas to technical and non-technical audiences.
• Ability to learn new skills and technologies quickly.
• Initiative and ownership, with the ability to build where needed and work autonomously.
• A solution-oriented mindset.

Nice To Haves

• Mechanistic interpretability experience.
• Contributions to open-source safety or evaluation tools and datasets.

Responsibilities

• Design and develop novel, high-impact benchmarks and environments that assess real-world behavior, including reward hacking, scheming, deception, and other misaligned behavior in frontier models and agents, including multi-agent systems.
• Conduct research to ensure benchmarks are valid, reliable, and meaningful.
• Collaborate with foundation model labs and enterprises to understand evolving safety evaluation needs.
• Analyze model behavior across benchmarks and articulate results.
• Publish research findings and contribute to the broader safety and evaluation research communities.
• Stay current with developments in LLM capabilities and alignment evaluation methodologies.

Benefits

• Highly competitive salary and meaningful ownership.
• Relocation and transportation support.
• Health and dental insurance coverage.
• Lunch and dinner provided, plus free snacks, coffee, and drinks.
• Unlimited PTO.
• $1,500 housing stipend for housing within a one-mile radius.
• Opportunity to collaborate with leading AI labs and work on the front lines of AI development and evaluations.
• Opportunity to publish and present work.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed