Ai Engineer - Responsible Ai

Centific Global

Seattle, WA, US
Base: $150k - $160k; bonus/equity: not specified; ...
Fully remote
Llm jailbreak attack and defense strategies
Production deployment of ml models
Python and pytorch/jax programming
The role involves translating pioneering research into robust, scalable security systems that resist adversarial and behavioral exploits at enterprise scale

Job Summary

  • The role involves translating pioneering research into robust, scalable security systems that resist adversarial and behavioral exploits at enterprise scale.
  • Candidates will own high-impact projects from research conception through production deployment, directly contributing to the platform's security guarantees.
  • The company offers a unique opportunity to bridge the gap between cutting-edge research and mission-critical product focus with real impact on core features.

Matching Summary

The role involves translating pioneering research into robust, scalable security systems that resist adversarial and behavioral exploits at enterprise scale.

Salary

Base: $150K - $160K; Bonus/Equity: Not specified; Benefits: Not specified

Skills & Requirements

Must-have

  • LLM jailbreak attack and defense strategies
  • Production deployment of ML models
  • Python and PyTorch/JAX programming
  • Distributed safety evaluation pipelines
  • Containerization with Docker and Kubernetes

Nice-to-have

  • Experience with multi-agent architectures
  • Adversarial prompt engineering expertise
  • Large-scale data processing frameworks
  • First-author publications in AI safety
  • Infrastructure as Code with Terraform

Key Requirements

  • Master's degree in CS/EE/ML/Security or related field
  • Ph.D. preferred
  • 2+ years of industry experience in applied ML/AI
  • Track record of publications in AI Safety or NLP robustness
  • Demonstrated experience in LLM jailbreak attacks or defense

Work Rights

Not specified

Tailored Resume

Cover Letter