SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Join Optibus' GenAI team to build and extend a production LLM agent system embedded across the product suite. The platform is a sophisticated AI assistant backed by a RAG knowledge base and evaluation-driven development workflow, already shipping to customers.
You'll own end-to-end responsibilities across the AI platform stack: design and evolve LLM agents with tool use, routing, and human-in-the-loop capabilities; implement tools and integrations that expose product capabilities to the agent via internal APIs and MCP servers, handling multi-tenant context; drive retrieval quality across the RAG pipeline including ingestion, embeddings, vector search, and reranking; define and evolve integration contracts with host application teams to embed the assistant into product UIs across different frontend stacks; and operate the platform including deployments, observability, and LLM service performance and cost optimization.
Key responsibilities include writing evaluators (rule-based, LLM-as-judge, multi-turn), maintaining CI evaluation gates, and using traces and feedback to debug production behavior. You'll establish engineering practices for AI-specific work including prompt versioning, evaluation coverage, testing, and code review standards.
This is a high-impact role for someone who wants to work on production AI systems at scale, with exposure to the full stack from agent design through infrastructure and observability.
