Research Engineer - AI Safety Systems and Guardrails

What you'll do

• Develop and deploy safety models, guardrails, risk detection, and defenses against adversarial inputs and unsafe agent behavior.
• Set technical direction for a safety research area and lead cross-functional initiatives from research through production evaluation.
• Monitor and improve deployed safeguards, balancing risk reduction with task completion, privacy, latency, cost, and reliability.

What they ask for

• Bachelor's degree in Computer Science, Computer Engineering, a relevant technical field, or equivalent practical experience.
• Research track record in one or more listed areas, supported by original or materially improved methods and rigorous experimental evidence.
• 3+ years of experience deploying machine learning models and systems at scale in an industry setting.
• Hands-on Python and deep-learning framework experience, such as PyTorch, including developing, training or fine-tuning, debugging, and evaluating models.

Nice to have

• Advanced degree (MS or PhD) in a related technical field, or equivalent advanced research experience.
• Experience with deployed AI safety guardrails, adversarial evaluation, agent safety, efficient inference, or distributed ML systems.

Pay

$183,997/year to $257,000/year (base salary); bonus + equity (amount not stated)

Tools

Python, PyTorch

AI focus

AI safety research and engineering: guardrails, policy-adaptable risk detection, adversarial robustness, and safe behavior for language models, multimodal systems, and AI agents.