Senior Agentic AI Engineer

Recruits Lab; United States; On-site; USD 140,000 - 200,000; Full time

Job summary

Recruits Lab is partnering with a high-growth technology company to build a large-scale agentic AI engineering organization. This hands-on role focuses on shipping production AI systems that reason, plan, remember, and orchestrate tools, with strong emphasis on reliability and observability.

You will design multi-step workflows, integrate with enterprise APIs and databases, and contribute to standards that ensure safe, scalable deployments.

Qualifications

• 4–8+ years of software engineering experience.
• Hands-on production AI/ML or LLM-based systems.
• Experience with agentic AI, not just prompt engineering.
• Experience with frameworks such as LangGraph, LangChain, AutoGen, LlamaIndex.
• Experience with tool/function calling, agent orchestration, memory, RAG, and structured outputs.
• Strong understanding of LLM evaluation, observability, reliability, and production monitoring.
• Experience integrating AI systems with APIs and enterprise applications.
• Strong software engineering fundamentals, system design, and debugging ability.

Responsibilities

• Build and deploy production-grade agentic AI systems.
• Design multi-step workflows involving reasoning, planning, memory, and tool use.
• Integrate agents with enterprise systems, APIs, databases, and internal platforms.
• Improve reliability, latency, evaluation, monitoring, and failure recovery.
• Build RAG and retrieval systems where appropriate.
• Develop evaluation frameworks for agent quality and task completion.
• Debug complex LLM and tool‑orchestration failures.
• Collaborate with product and engineering teams to move AI systems from prototype to production.
• Help establish engineering standards and best practices for agentic systems.

Skills

Agentic AI

Production AI/ML systems

LLM frameworks

Tool calling & orchestration

Memory & RAG

Observability & reliability

APIs & enterprise integration

Debugging & system design

Strong English communication

Tools

LangGraph

LangChain

AutoGen

LlamaIndex

Job description

Recruits Lab is partnering with a high-growth technology company building a large-scale Agentic AI engineering organization. The team is hiring multiple engineers to design, build, deploy, and improve production AI agents used in complex enterprise environments.

This is a hands‑on engineering role for someone who has gone beyond prototypes and has experience shipping reliable AI systems that use tool calling, planning, memory, retrieval, orchestration, evaluation, and observability.

What You’ll Do

• Build and deploy production‑grade agentic AI systems
• Design multi‑step workflows involving reasoning, planning, memory, and tool use
• Integrate agents with enterprise systems, APIs, databases, and internal platforms
• Improve reliability, latency, evaluation, monitoring, and failure recovery
• Build RAG and retrieval systems where appropriate
• Develop evaluation frameworks for agent quality and task completion
• Debug complex LLM and tool‑orchestration failures
• Collaborate with product and engineering teams to move AI systems from prototype to production
• Help establish engineering standards and best practices for agentic systems

What We’re Looking For

• Approximately 4-8+ years of software engineering experience
• Strong hands‑on experience building production AI/ML or LLM‑based systems
• Proven experience with agentic AI, not just prompt engineering or chatbot development
• Experience with frameworks such as LangGraph, LangChain, AutoGen, LlamaIndex, or similar
• Experience with tool/function calling, agent orchestration, memory, RAG, and structured outputs
• Strong understanding of LLM evaluation, observability, reliability, and production monitoring
• Experience integrating AI systems with APIs and enterprise applications
• Strong software engineering fundamentals, system design, and debugging ability

Especially Valuable

• Experience deploying agentic systems in regulated or enterprise environments
• Experience with platforms such as Salesforce, ServiceNow, Slack, Jira, SharePoint, or SQL‑based systems
• Experience with human‑in‑the‑loop workflows
• Experience building evaluation harnesses and automated testing for AI agents
• Experience improving reliability of multi‑agent or multi‑step AI systems

Requirements

• Must be based in the United States
• Must be authorized to work in the U.S. without current or future sponsorship
• Full‑time employment only
• Strong professional English communication skills

Ideal Background

You’ve personally built AI systems that do more than answer questions. You’ve shipped agents that take actions, interact with tools, manage state, recover from failures, and operate reliably in real production environments.

This is not a prompt‑engineering‑only role. Production engineering depth is essential.