Lead ML Engineer, AI Identity Security

Okta; San Francisco (CA); Hybrid; USD 238,000 - 326,000; Full time

Benefits offered by this job

Equity

Bonus

Health insurance

Dental insurance

Vision insurance

401(k)

Flexible spending account

Paid leave

Job summary

Okta is seeking a Principal ML Engineer to advance AI agent authorization. You will replace static rule systems with dynamic AI security, delivering real-time threat inspection, agent intent evaluation, and behavioral analysis to ensure autonomous agents operate safely within bounds.

You will architect the unified control plane and drive features that enable a scalable Identity Security Fabric for the agentic era, guiding a team of engineers and collaborating with product partners.

Qualifications

• 10+ years of software development experience.
• Hands-on experience with applied machine learning and modern Generative AI platforms.
• Experience with retrieval-augmented generation (RAG) and embeddings.
• Familiarity with ML frameworks and orchestration tools.

Responsibilities

• Implement intent-based enforcement for agent runtime requests.
• Apply LLM reasoning and prompt parsing in real time.
• Integrate lightweight inference engines into API gateway path.
• Use embeddings or vector search to score alignment between intent and actions.
• Design confidence-scored decision engines and guardrails.
• Establish evaluation benchmarks and defenses against prompt injection.
• Architect scalable ML/GenAI systems with retrieval, inference, and evaluation pipelines.
• Optimize prompting and RAG workflows for Claude-based systems.
• Build automated evaluation pipelines for model quality and safety.
• Implement schema validation and guardrails for reliable AI outputs.
• Mentor engineers to support team growth.

Skills

Python

Machine Learning

LLM platforms

Retrieval augmented generation

LangChain

LangGraph

LlamaIndex

MCP

FastAPI

PyTorch

Education

Bachelor’s or Master’s degree in Computer Science or related field

Tools

AWS Bedrock

OpenAI

Job description

Okta is seeking a Principal ML Engineer to advance AI agent authorization. You will replace static rule systems with dynamic AI security, delivering real-time threat inspection, agent intent evaluation, and behavioral analysis to ensure autonomous agents operate safely within bounds.

You will architect the unified control plane and drive features that enable a scalable Identity Security Fabric for the agentic era, guiding a team of engineers and collaborating with product partners.