Senior Software Engineer (Applied AI)

Join Okta, a leading identity and security company, as a Senior Software Engineer in the Applied AI team. You will work on building Digital Workers, autonomous agents for identity operations and security. This role offers the opportunity to shape the product with the ownership and pace of a startup, while benefiting from the resources of a public company. You will be responsible for building the agent harness, integrating model APIs, evaluating existing harnesses, and improving prompts and model routing.

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

Responsibilities

• Contribuer à la conception et au développement de travailleurs autonomes pour les opérations d'identité et la sécurité.
• Construire des systèmes d'évaluation et de validation pour garantir la fiabilité des agents autonomes.
• Intégrer des API de modèles d'IA et sélectionner des modèles en fonction de la qualité mesurée, de la latence et du coût.
• Strong owner: You follow an improvement through code, evaluation, release and customer use
• Production builder: You have shipped AI software and know what changes when real users depend on it
• Careful evaluator: You investigate failures and use evidence to judge quality
• Strong Python engineering skills and experience shipping an LLM application that uses tools

Requirements

• 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
• Depth in agent execution or evaluation systems, with working code and failure analysis you can explain
• Ability to distinguish a plausible model response from a supported finding or verified action
• 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
• Open-source contributions, agent observability, security evaluations or synthetic evaluation data

Preferred

• Fine-tuning, preference data, post-training evaluation or model distillation using approved datasets
• Identity and security workflows. Foundation-model research experience is optional

Pay

USD 165,000 - 226,000