Staff Software Engineer (Applied Artificial Intelligence)

Join Okta, a leading identity and security company, as a Staff Software Engineer specializing in Applied Artificial Intelligence. You will work directly with the CEO and have the opportunity to shape a new suite of autonomous agents for identity operations and security. Your responsibilities will include building reliable agent harnesses, integrating model APIs, evaluating existing systems, and leading a domain within the team. This role offers the ownership and pace of a startup with the resources of a public company.

• Contribuer à la construction de travailleurs autonomes pour les opérations d'identité et la sécurité.
• Développer des systèmes d'évaluation et de test pour garantir la fiabilité des agents.
• Intégrer des API de modèles d'IA et sélectionner des modèles en fonction de la qualité mesurée.

• Production builder: You have shipped AI software and know what changes when real users depend on it
• Strong owner: You follow an improvement through code, evaluation, release and customer use
• Careful evaluator: You investigate failures and use evidence to judge quality
• Hands-on experience building agent workflows or evaluation systems for tool-using LLM applications. For harness work, relevant experience includes Claude Agent SDK, OpenAI Codex SDK, Strands Agents, LangChain Deep Agents, LangGraph or a custom implementation
• Experience integrating model APIs, structured outputs and asynchronous services. Experience with OpenAI or Anthropic is especially relevant
• Strong Python engineering skills and experience shipping an LLM application that uses tools
• Depth in agent execution or evaluation systems, with working code and failure analysis you can explain
• Our core stack is Python FastAPI, AWS Step Functions, Amazon Bedrock AgentCore, PostgreSQL on Amazon RDS and pgvector. OpenAI and Anthropic model APIs are part of the integration plan
• We plan to add an agent harness and a dedicated analytics layer using ClickHouse or BigQuery. The harness choice is open. Experience with equivalent tools also counts
• Ability to distinguish a plausible model response from a supported finding or verified action
• Open-source contributions, agent observability, security evaluations or synthetic evaluation data
• Fine-tuning, preference data, post-training evaluation or model distillation using approved datasets
• Identity and security workflows. Foundation-model research experience is optional