Member of Technical Staff - Safety

Reflection AI
San Francisco, New York, London
Workplace: OnsiteFull timeFunction: Administration & Executive AssistanceEducation: mastersSkills: ["Problem-solving","Collaboration","Communication"]

Role focuses on leading red-teaming and adversarial evaluation for Reflection’s open weight models, translating safety findings into guardrails, and ensuring releases meet risk thresholds. You’ll develop scalable safety benchmarks, research jailbreaking defenses, and collaborate with the Alignment team in a fast-paced startup to advance open AI safety and model reliability.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Reflection AI
Reflection AI
7 months ago

Member of Technical Staff - Safety

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 19 hours agoStatus: Live

Job Summary

Role focuses on leading red-teaming and adversarial evaluation for Reflection’s open weight models, translating safety findings into guardrails, and ensuring releases meet risk thresholds. You’ll develop scalable safety benchmarks, research jailbreaking defenses, and collaborate with the Alignment team in a fast-paced startup to advance open AI safety and model reliability.
Location: San Francisco, New York, London
Workplace: Onsite
Employment Type: Full time
Job Function: Administration & Executive Assistance

Key Responsibilities

  • •Own the red-teaming and adversarial evaluation pipeline for Reflection’s models, continuously probing for failure modes across security, misuse, and alignment gaps.
  • •Work hand-in-hand with the Alignment team to translate safety findings into concrete guardrails, ensuring models behave reliably under stress and adhere to deployment policies.
  • •Validate that every release meets the lab’s risk thresholds before it ships, serving as a critical gatekeeper for our open weight releases.
  • •Develop scalable, automated safety benchmarks that evolve alongside our model capabilities, moving beyond static datasets to dynamic adversarial testing.
  • •Research and implement state-of-the-art jailbreaking techniques and defenses to stay ahead of potential vulnerabilities in the wild.

Pay and Benefits

Perks:Health InsuranceWellness StipendParental LeaveRelocationSalaryEquity

Key Requirements

  • •MS or PhD in Computer Science, Machine Learning, or related discipline, or equivalent practical experience in AI Safety.
  • •Deep technical understanding of LLM safety, including adversarial attacks, red-teaming methodologies, and interpretability.
  • •Strong software engineering capabilities with experience building automated evaluation pipelines or large-scale ML systems.
  • •Experience with Reinforcement Learning (RLHF/RLAIF) and how it impacts model safety and alignment is a strong plus.
  • •Thrive in a fast-paced, high-agency startup environment with bias toward action.
Experience:AI safetyLLM safety
Education:Master's
Skills:Problem-solvingCollaborationCommunication
Tech Stack:Reinforcement learningRed-teamingInterpretabilityLarge-scale ML systems

Company Brief

Reflection AI
Builds frontier autonomous AI systems focused on autonomous coding agents (product: Asimov) to create organizational superintelligence, founded by former DeepMind/Google researchers and hiring across SF, NYC, London.
Industry: AI & Machine Learning
Company Size: Small (11 to 50 employees)
Growth: Growth Stage Startup
Funding: Series A
Headquarters: San Francisco, United States
Founded: 2024
WebsiteLinkedInGlassdoor