Added
23 days ago
Type
Full time
Salary
Upgrade to Premium to se...
Related skills
python kubernetes gcp go langchainπ Description
- Champion Secure Agentic AI Development; adapt security for RL and agent systems.
- Agentic threat modeling; identify risks like goal misalignment and reward hacking.
- Secure agent architecture & safety boundaries; deterministic guardrails and Zero Trust.
- Secure agent tools & memory; prevent manipulation and memory poisoning.
- MLSecOps for RL pipelines; protect training and simulation environments.
- Adversarial testing & red teaming; probe for behavioral manipulation.
π― Requirements
- Agentic AI & RL security: experience with RL, autonomous agents.
- AI partnership: embedded with AI researchers; bridge probabilistic AI and deterministic code.
- Core experience: 5+ years in product security or related security engineering role.
- Safety mindset: prioritize availability and safety; familiar with fail-safes and human-in-the-loop.
- Technical depth: Python (essential) or Go; RL libraries like Ray.
- Advanced MLOps: Kubeflow/MLflow and securing data and model-training pipelines.
π Benefits
- 100% remote company with asynchronous collaboration.
- Competitive compensation and meaningful equity.
- Training, development, and professional growth opportunities.
- Medical, dental, and vision insurance (regional variations).
- Unlimited PTO with a minimum of 20 days/year.
- Paid parental leave and workspace stipends.
Meet JobCopilot: Your Personal AI Job Hunter
Automatically Apply to Engineering Jobs. Just set your
preferences and Job Copilot will do the rest β finding, filtering, and applying while you focus on what matters.
Help us maintain the quality of jobs posted on Empllo!
Is this position not a remote job?
Let us know!