Senior Software Engineer, AI

Okta•San Francisco, CA

3h•Hybrid

About The Position

Identity is the key to unlocking the potential of AI. Okta secures AI by building the trusted, neutral infrastructure that enables organizations to safely embrace this new era. This work requires a relentless drive to solve complex challenges with real-world stakes. We are looking for builders and owners who operate with speed and urgency and execute with excellence. This is an opportunity to do career-defining work. We're all in on this mission. If you are too, let's talk. Okta’s Business Technology organization builds secure and intelligent internal platforms that power our global workforce. Our AI & Automation team is delivering next-generation tools and experiences by integrating GenAI and intelligent automation into workflows across IT, HR, Finance, Sales, Marketing and Customer Support. We focus on real-world applications: virtual agents, AI copilots, internal RAG services, and AI-augmented self-service portals — all with scale, governance, and user experience in mind. As a Senior Software Engineer, Applied AI, you’ll play a key role in building user-facing and backend systems that leverage GenAI to improve internal experiences and operations. This role requires strong full-stack engineering skills, with an emphasis on both AI integration and building intuitive, performant UIs that make AI accessible and useful to our internal customers. You’ll work closely with software engineers, product managers, and designers to build secure, intelligent tools for employees across Okta.

Requirements

5–8 years of software engineering experience with full-stack development, including 2+ years of building AI/ML-driven applications.
Strong Python development skills and 5+ years experience building cloud-based services using AWS, Docker, and RESTful APIs.
2+ years of experience in frontend technologies like React, TypeScript, or Vue, and comfort working on UI/UX for internal tools or enterprise applications.
Hands-on experience with LLM integration, RAG pipelines, prompt engineering, or orchestration frameworks like LangChain or LlamaIndex.
Strong background in distributed systems, APIs, microservices, container orchestration (ECS/EKS), and cloud platforms (AWS/GCP/Azure).
Familiarity with secure coding, authentication/authorization, and internal data governance best practices.
Ability to collaborate across engineering, design, and product teams — with a strong sense of user empathy and technical ownership.

Nice To Haves

Exposure to design systems, AI evaluation tooling, or real-time application performance monitoring.

Responsibilities

Design and build end-to-end GenAI-powered applications, including web-based UIs, API services, and backend orchestration.
Implement and integrate LLM-based experiences using frameworks like LangChain, LlamaIndex, and tools like OpenAI, Claude, or Gemini.
Define, implement, and champion operational excellence standards (SLOs, observability, incident response frameworks) for all services deployed.
Develop responsive, accessible, and modern frontend interfaces using frameworks like React or Vue — with a focus on usability, performance, and trust in AI outputs.
Build and maintain a library of reusable frontend components and hooks that allow other business delivery teams to easily "drop in" GenAI capabilities into their own applications.
Build and maintain retrieval-augmented generation (RAG) pipelines with vector search and embedding strategies (e.g., Pinecone, FAISS, Qdrant).
Collaborate with designers and product managers to rapidly iterate on UX patterns for AI-powered experiences (e.g., prompt inputs, citations, summaries).
Ensure security, privacy, observability, and test coverage across the full stack.
Contribute to architecture decisions, engineering standards, and best practices for AI/automation systems.
Partner with platform and infrastructure teams to ensure services scale reliably across the org.