AI forward deployment engineer

We are a smart AI b2b saas startup looking for AI Forward Deployed Engineer As our AI Forward Deployed Engineer, you'll be the technical owner of getting our product live and performing inside our customers' businesses. You'll embed with customers, understand their support workflows, configure and tune AI agents, build integrations, and drive resolution rates up until the agent is delivering real value. What you'll do Own end-to-end implementation for new customers — from kickoff to a live, high-performing AI agent. Configure, test, and tune AI agents to hit resolution targets, iterating on real ticket data and eval results. Build and validate integrations with customer systems (Zendesk, Intercom, internal APIs, knowledge bases, and more). Partner directly with customer stakeholders (support leaders, ops, engineering) to define success criteria and drive toward them. Act as the trusted technical advisor that expands accounts and keeps customers happy. Tech stack & tools you'll work with Languages: Python; AI / LLMs: OpenAI and Anthropic APIs, prompt engineering, RAG pipelines, vector databases (e.g., Pinecone, pgvector), and building evals to measure agent quality. Agent loops, agent harness. What we're looking for 2+ years in a technical, customer-facing role — forward deployed / solutions / implementation engineering, technical consulting, or similar. Experience with LLMs / AI agents — prompt engineering, RAG, or evals — or strong enthusiasm and aptitude to go deep fast.