jobapplier

Principal Software Engineer (Applied AI)

Okta

Skills

Required

  • OpenAI / Anthropic
  • model APIs
  • agent execution / evaluation systems
  • LLM
  • working code
  • Python engineering
  • structured outputs
  • asynchronous services
  • agent observability / security evaluations / synthetic evaluation

Preferred

  • preference data / post-training evaluation / model distillation
  • approved datasets
  • Identity and security workflows
  • evaluation

Join Okta, a leading identity and security company, as a Principal Software Engineer (Applied AI). You will be part of the team that built Jeeva AI and is now developing Digital Workers, a suite of autonomous agents for identity operations and security. You will work directly with Okta's co-founder and CEO, Todd McKinnon, and have the opportunity to shape the product for Okta's 20,000+ customers. Your responsibilities will include 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

USD 224,000 - 308,000

Responsibilities

  • Contribuer à la construction de travailleurs autonomes pour les opérations d'identité et la sécurité au sein d'Okta.
  • Développer des systèmes d'évaluation et des harnais pour garantir la fiabilité des agents autonomes.
  • Intégrer les API de modèles OpenAI et Anthropic, et évaluer la qualité, la latence et le coût des modèles.
  • 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

Requirements

  • Depth in agent execution or evaluation systems, with working code and failure analysis you can explain
  • Strong Python engineering skills and experience shipping an LLM application that uses tools
  • Ability to distinguish a plausible model response from a supported finding or verified action
  • Experience integrating model APIs, structured outputs and asynchronous services. Experience with OpenAI or Anthropic is especially relevant
  • 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

Every job at Okta