AI Engineer Agent Development (GenAI / LLMs)

Job Description

Deep hands-on experience with Agentic AI, RAG, and production deployments

Strong understanding of scaling, monitoring, and operational support

Ownership of architecture and implementation decisions

Ability to clearly and confidently articulate technical depth and real-world experience

OVERVIEW

We are building an intelligent agent platform for a large-scale healthcare enterprise serving ~9,000 locations and millions of daily interactions.

This role focuses on developing and optimizing LLM-powered agents that drive real-world workflows scheduling, location-based services, and patient-facing engagement as part of a greenfield build on a fast-moving team.

WHAT YOU'LL DO

• Design, develop, and deploy AI agents using LLM frameworks (LangChain, LangGraph, ADK, or equivalent)
• Build agent workflows that support high-throughput, real-time user interactions
• Integrate agents with internal and external APIs: scheduling, location services, and healthcare data sources
• Partner with QA and validation teams to test and productionize agent capabilities
• Troubleshoot and optimize agent performance within the platform
• Expand agent use cases as business needs evolve

MUST-HAVE QUALIFICATIONS

• 5-8 years building AI/LLM-based applications or agents in production environments
• 1-2 years hands-on with LangChain, LangGraph, ADK, or similar orchestration frameworks
• Strong API integration experience with real-time data workflows
• Python proficiency for backend and AI development
• Experience working in structured environments with QA and validation processes
• Able to move fast and operate effectively in high-urgency, ambiguous settings

NICE TO HAVE

• Experience on high-scale systems with millions of daily interactions
• Conversational AI, IVR, or workflow automation agent experience
• Familiarity with healthcare, retail, or location-based service ecosystems
• Exposure to enterprise or internal AI platforms