Senior Gen-AI Engineer
Core
Design, develop, and maintain scalable Python-based APIs and backend services; build, deploy, and optimize production-grade LLM applications including RAG solutions, multi-agent systems, and MCP servers.
Role type
Senior Gen-AI Engineer (Backend & LLM Infrastructure)
Builds
Production-grade LLM applications, RAG solutions, multi-agent systems, and scalable AI infrastructure.
Domain
Generative AI, Large Language Models, Backend Engineering, Event-driven Architecture
Deliverable
production ML models | product features | infrastructure
Required skills
Python (FastAPI), LLM API integration (OpenAI, Anthropic), RAG system design, vector databases, semantic search, multi-agent orchestration, MCP server development, prompt engineering, event-driven architecture, system debugging, security best practices
Preferred skills
LLM guardrails, LLM frameworks (LangChain, LlamaIndex), LLM monitoring and observability, evaluation harnesses, LLM-as-judge metrics
Technologies
Python, FastAPI, OpenAI, Anthropic, vector databases, MCP servers, Claude Code, Cursor, GitHub Copilot
Responsibilities
Design and implement end-to-end RAG solutions with vector databases and semantic search; build and orchestrate multi-agent systems to automate workflows; develop and manage secure, scalable MCP servers; create, test, and refine prompts and agent instructions; implement event-driven architectures and messaging systems; monitor and optimize AI and backend systems for performance and reliability.
Seniority
Senior, hands-on IC