Staff ML Engineer: AI Identity Security Fabric

Okta; Toronto (OH); Hybrid; USD 118,000 - 162,000; Full time

Job summary

Okta is seeking a Staff Machine Learning Engineer to join the Agent Access Policies sub-team within Okta Secures AI. You will advance authorization capabilities by replacing static rules with dynamic AI security mechanisms, delivering real-time threat inspection and behavior analysis for autonomous AI agents within defined bounds.

You will architect the unified control plane to establish the Identity Security Fabric for the agentic era, aligning with the guiding principle: get AI right, identity

Qualifications

• 8+ years of software development experience.
• Strong programming in Python; familiarity with Go or TypeScript is a plus.
• Hands-on experience with modern Generative AI platforms (AWS Bedrock, OpenAI, Anthropic, etc.).
• Experience with retrieval-augmented generation (RAG), embeddings, and knowledge-base workflows.
• Experience with AI agent frameworks (LiteLLM, LangGraph, LangChain, LlamaIndex, MCP).
• Knowledge of ML frameworks (FastAPI, PyTorch, TensorFlow, Spark ML) and orchestration tools (Airflow).
• Experience defining evaluation metrics, pipelines, and feedback loops for ML/GenAI systems.
• Bachelor’s or Master’s in Computer Science or related field.

Responsibilities

• Implement intent-based enforcement to verify agent runtime requests align with purpose.
• Apply LLM reasoning to interpret prompts, tool payloads, and intent in real time.
• Integrate low-latency inference/semantic engines into API gateway paths.
• Use embeddings and vector search to score alignment between intent and actions.
• Design evaluation benchmarks and guardrails to prevent bypasses.
• Architect scalable ML/GenAI systems with retrieval, inference, and evaluation pipelines.
• Optimize prompting, retrieval, and RAG workflows for Claude-based systems.
• Build automated evaluation pipelines to measure model quality and safety.

Skills

Python

ML Engineering

Go

TypeScript

AI agent frameworks

Education

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

Tools

AWS Bedrock

OpenAI

Anthropic

LangGraph

LangChain

LlamaIndex

MCP

PyTorch

TensorFlow

FastAPI

Spark ML

Airflow

Job description

Okta is seeking a Staff Machine Learning Engineer to join the Agent Access Policies sub-team within Okta Secures AI. You will advance authorization capabilities by replacing static rules with dynamic AI security mechanisms, delivering real-time threat inspection and behavior analysis for autonomous AI agents within defined bounds.

You will architect the unified control plane to establish the Identity Security Fabric for the agentic era, aligning with the guiding principle: get AI right, identity