Senior AI Platform Engineer / Technical Lead

We’re seeking a hands-on technical lead to build an enterprise AI agent platform for a venture. You’ll own the initial architecture and production implementation, enabling enterprise clients to deploy agents using privately hosted models, frontier model APIs, or both. Job Description (CTO role) - Build an LLM gateway with model routing, access policies, usage tracking, cost controls, and approved fallback behavior. - Develop enterprise agents that process documents, answer customer inquiries, and update business records. - Create reusable integrations, retrieval pipelines, evaluation suites, and deployment templates. - Deploy and operate cloud and private model infrastructure with monitoring, tracing, and automated delivery. - Implement authentication, tenant isolation, secrets management, audit logging, and sensitive-data controls. - Work directly with client teams, lead technical delivery, and prepare documentation and operational handover. Five Required Skills - Production AI Agents and LLM Gateways - Demonstrated experience with tool execution, workflow orchestration, model routing, evaluations, and human approvals. - Python and TypeScript Backend Development - Strong production API, distributed systems, and enterprise integration experience. - RAG and Data Engineering - PostgreSQL, vector databases, document ingestion, retrieval quality, and performance optimization. - Cloud Infrastructure and Model Serving - GCP, Docker, Kubernetes, CI/CD, and deployment of open-weight models. - Security and Technical Leadership - Access control, data boundaries, observability, architecture ownership, client communication, and engineering leadership. Candidates must provide verifiable examples of their own production work and explain their architectural decisions and measured results. Intro Video Require.