Okta is building Okta Secures AI for the agentic era, transforming authorization for agent access policies with dynamic AI security mechanisms. In this Principal Machine Learning Engineer role (hybrid in San Francisco, CA), you will help advance intent-aware enforcement and real-time threat inspection by replacing static rule-based approaches with a unified control plane within Okta’s Identity Security Fabric.
What you’ll do
- Implement intent-based enforcement to verify agent runtime requests align with intended purpose, including required key capabilities.
- Apply LLM reasoning and prompt parsing to interpret prompts, tool payloads, and intent in real time.
- Integrate low-latency inference or semantic evaluation engines directly into the API gateway request path.
- Use embeddings, vector search, or zero-shot classification to score alignment between agent intent and executed actions.
- Design confidence-scored decision engines that feed semantic verification results into policy frameworks (for example, Cedar).
- Establish evaluation benchmarks and prompt injection defenses with guardrails to reduce bypasses and false positives.
- Architect scalable ML and Generative AI systems that integrate retrieval, inference, and evaluation pipelines.
- Optimize prompting, context retrieval, and RAG workflows for accuracy, safety, and efficiency in Claude-based systems.
- Build automated evaluation pipelines to measure model quality, correctness, groundedness, and safety in production.
- Implement schema validation, structured output enforcement, and guardrails to support reliable and compliant AI outputs.
- Mentor and coach engineers to strengthen the team and community.
What you bring
- 10+ years of software development experience, with strong programming expertise in Python (familiarity with Go or Typescript is a plus).
- Hands-on applied machine learning experience, from feature engineering to training and fine-tuning models.
- Hands-on experience with modern Generative AI platforms (such as AWS Bedrock, OpenAI, Anthropic, etc.).
- Deep understanding of retrieval-augmented generation (RAG), embeddings, and knowledge-base workflows.
- Hands-on experience with AI agent frameworks including LiteLLM, LangGraph, LangChain, LlamaIndex, MCP, or similar.
- Familiarity with ML frameworks and tooling such as FastAPI, PyTorch, TensorFlow, Spark ML, and workflow orchestration tools like Airflow.
- Experience defining evaluation metrics, pipelines, and feedback loops for ML/GenAI systems.
- Proven collaboration with product and engineering teams to drive greenfield initiatives, manage unknowns, and iterate quickly.
- Experience building tools or infrastructure for AI/ML applications, with a deep understanding of the developer lifecycle in an AI-native world.
Technologies you may work with
Python, Go, Typescript, AWS Bedrock, OpenAI, Anthropic, LiteLLM, LangGraph, LangChain, LlamaIndex, MCP, FastAPI, PyTorch, TensorFlow, Spark ML, Airflow, Cedar, Claude-based systems
Compensation
USD 238,000 - 326,000 per year
Education
Bachelor’s or Master’s degree in Computer Science or related field
Benefits
- Equity (where applicable), bonus, and benefits including health, dental, and vision insurance
- 401(k) and flexible spending account
- Paid leave, including PTO and parental leave
Extra credit
- Experience integrating AI-driven systems with identity, authentication, or security products
- Exposure to ethical AI, model risk, or compliance frameworks
- Familiarity with evaluation datasets, synthetic data generation, or LLM-as-a-judge methods
Okta culture
- Supporting Your Well-Being
- Driving Social Impact
- Developing Talent and Fostering Connection + Community
