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 integrated into multiple host applications, backed by a RAG knowledge base and an evaluation-driven development workflow that already ships to customers.
You will work end-to-end across the full stack: designing and evolving LLM agents with tool use, routing, and human-in-the-loop flows; implementing tools and integrations that expose product capabilities to the agent via internal APIs and MCP servers; owning retrieval quality across the RAG pipeline including ingestion, embeddings, vector search, and reranking; defining and evolving host integration contracts in collaboration with product teams; and driving evaluation-led development by writing evaluators (rule-based, LLM-as-judge, multi-turn) and maintaining CI eval gates.
You will also operate the platform, owning deployments, observability, and the performance and cost of LLM-backed services. A key part of the role is establishing engineering practices for AI-specific work: prompt versioning, eval coverage, testing, and code review standards.
This is a high-impact role where you'll extend the platform's quality bar, define its future direction, and work across agent design, infrastructure, product integration, and production operations. You'll collaborate with host application teams across different frontend stacks and contribute to both technical depth and organizational practices around AI development.
