SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: CAD 168,000 - 231,000 / annual
Okta is building the identity security infrastructure for the AI agent era. The Okta Secures AI team is creating a unified control plane to manage identity, access, and security for autonomous AI agents—moving identity from reactive gatekeeper to proactive risk mitigation.
As a Staff Machine Learning Engineer on the Agent Access Policies sub-team, you will architect and implement ML-driven authorization systems that replace static, rule-based access controls with dynamic, real-time threat inspection and behavioral analysis. Your work will ensure AI agents operate safely within specified bounds while maintaining enterprise-scale performance.
Key responsibilities include:
- Designing intent-based enforcement mechanisms to verify agent runtime requests match their intended purpose
- Applying LLM reasoning and prompt parsing to interpret prompts, tool payloads, and agent intent in real time
- Integrating low-latency inference engines directly into API gateway request paths
- Using embeddings, vector search, and zero-shot classification to score alignment between agent intent and executed actions
- Building confidence-scored decision engines that feed semantic verification results into policy frameworks (e.g., Cedar)
- Establishing evaluation benchmarks, prompt injection defenses, and guardrails to prevent bypasses and false positives
- Architecting scalable ML and generative AI systems integrating retrieval, inference, and evaluation pipelines
- Optimizing prompting, context retrieval, and RAG workflows for accuracy, safety, and efficiency using Claude-based systems
- Building automated evaluation pipelines to measure model quality, correctness, groundedness, and safety in production
- Implementing schema validation, structured output enforcement, and guardrails for reliable, compliant AI outputs
You will collaborate closely with product managers, engineers, and designers to drive greenfield initiatives, navigate technical unknowns, and iterate rapidly. This is a high-impact role defining industry standards for agentic identity security.
REQUIREMENTS:
- 8+ years of software development experience with strong Python expertise (Go or TypeScript familiarity a plus)
- Hands-on experience with applied machine learning: feature engineering, model training, and fine-tuning
- Hands-on experience with modern generative AI platforms (AWS Bedrock, OpenAI, Anthropic, etc.)
- Deep understanding of retrieval-augmented generation (RAG), embeddings, and knowledge-base workflows
- Hands-on experience with AI agent frameworks: LiteLLM, LangGraph, LangChain, LlamaIndex, MCP, or similar
- Familiarity with ML frameworks (FastAPI, PyTorch, TensorFlow, Spark ML) and workflow orchestration (Airflow, etc.)
- Experience defining evaluation metrics, pipelines, and feedback loops for ML/GenAI systems
- Proven ability to collaborate with product and engineering teams on greenfield initiatives, navigate unknowns, and iterate quickly
- Experience building tools or infrastructure for AI/ML applications with deep understanding of developer lifecycle in AI-native environments
- Bachelor's or Master's degree in Computer Science or related field
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
