Agentic AI Engineer

Recruits Lab; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

Recruits Lab is searching for an exceptional Agentic AI Engineer to help build and deploy production‑grade AI agents and LLM‑powered systems.

This hands‑on role requires shipping agentic systems beyond prompts and basic chatbots, with work across tool calling, reasoning, planning, memory, and cross‑functional collaboration to move prototypes into production‑ready solutions.

Qualifications

• Strong software engineering background, preferably Python.
• Hands-on experience building production LLM applications.
• Experience with AI agents, tool calling, orchestration, or multi-agent systems.
• Experience with frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, Semantic Kernel, or similar.
• Strong understanding of RAG, APIs, structured data, and modern AI architecture.
• Proven ability to build and ship 0→1 products.
• Startup mindset with strong ownership and execution.

Responsibilities

• Build production AI agents and multi-step agentic workflows.
• Develop systems for tool calling, reasoning, planning, and memory.
• Integrate LLMs with APIs, databases, enterprise applications, and internal systems.
• Build RAG, knowledge retrieval, and orchestration systems.
• Improve agent reliability, evaluation, observability, and performance.
• Take AI products from prototype to production.
• Work cross‑functionally to identify high‑impact AI use cases.

Skills

Python

LLM apps

AI agents

AI frameworks

RAG & APIs

0→1 products

Startup mindset

Tools

LangGraph

LangChain

LlamaIndex

AutoGen

Semantic Kernel

Job description

We’re conducting a confidential search for an exceptional Agentic AI Engineer to help build and deploy production‑grade AI agents and LLM‑powered systems.

This is a hands‑on engineering role for someone who has actually built and shipped agentic systems—not just experimented with prompts or basic chatbots.

What You’ll Do

• Build production AI agents and multi‑step agentic workflows
• Develop systems for tool calling, reasoning, planning, and memory
• Integrate LLMs with APIs, databases, enterprise applications, and internal systems
• Build RAG, knowledge retrieval, and orchestration systems
• Improve agent reliability, evaluation, observability, and performance
• Take AI products from prototype to production
• Work cross‑functionally to identify high‑impact AI use cases

What We’re Looking For

• Strong software engineering background, ideally Python
• Hands‑on experience building production LLM applications
• Experience with AI agents, tool/function calling, orchestration, or multi‑agent systems
• Experience with frameworks such as LangGraph, LangChain, LlamaIndex, AutoGen, Semantic Kernel, or similar
• Strong understanding of RAG, APIs, structured data, and modern AI architecture
• Proven ability to build and ship 0→1 products
• Startup mindset with strong ownership and execution

Strong Plus

Experience at a leading AI company, high‑growth startup, frontier AI organization, or top‑tier technology company.

US‑based candidates only.

This search is being conducted confidentially. Additional company and role details will be shared with qualified candidates during the interview process.