AI Delivery Engineer (Agent Tooling and Code Generation)

Job description

AI Delivery Engineer — Agent Tooling & Code Generation

Builds and ships production-grade AI agent tooling and code-generation solutions, working closely with engineering and product teams to embed AI agents into the delivery lifecycle — from prototyping through reliable, monitored production rollout.

Key Responsibilities:

- Design, build, and maintain AI agent tooling that automates engineering and business workflows

- Develop and refine code-generation pipelines and developer copilots

- Integrate LLM APIs and agent-orchestration frameworks into production systems

- Build and maintain RAG pipelines, vector stores, and prompt-engineering workflows

- Identify high-value automation opportunities together with engineering and product teams

- Monitor, evaluate, and improve agent performance, reliability, and safety in production

- Document tooling and support internal teams adopting AI agents

Requirements:

- 4+ years of software engineering experience, with recent focus on applied AI/LLM systems

- Hands-on experience building LLM-based agents or agent-orchestration frameworks (e.g., LangChain, LangGraph, AutoGen, or custom pipelines)

- Experience with code-generation tooling, developer copilots, or AI-assisted development workflows

- Strong Python skills (TypeScript/JS a plus) for building agent tooling and integrations

- Experience with LLM APIs (OpenAI, Anthropic, etc.), RAG pipelines, and vector databases

- Proven ability to take AI prototypes from concept to reliable, production-grade delivery

- Understanding of prompt engineering, evaluation, and guardrails for LLM-based systems

Nice to Have:

- Experience deploying agentic frameworks in enterprise settings

- Familiarity with MLOps/LLMOps practices

- Contributions to open-source AI tooling