Lead GenAI / AI-ML SME – Agentic AI
Location: Denver, CO – Onsite
Work Arrangement: Onsite
Interview: Onsite client interview required
Employment Type: Contract – C2C / W2
Rate: $80–$85/hr C2C
Job Description
We are looking for a highly experienced Lead GenAI / AI-ML SME to lead and contribute hands-on to an Agentic AI program focused on network anomaly detection, investigation, and operational intelligence.
This role requires a strong combination of hands-on GenAI engineering, Agentic AI architecture, technical leadership, and client-facing communication.
The ideal candidate will have experience designing and deploying production-grade AI/ML and LLM applications using Python, LangChain, LangGraph, RAG, vector databases, LLM agents, and multi-agent workflows.
Important: Candidates must currently reside in the Denver, CO area and must be available for an onsite client interview and onsite work.
Key Responsibilities
Lead the technical design and implementation of GenAI and Agentic AI solutions.
Build production-grade LLM applications using Python.
Design and develop LLM agents and multi-agent workflows.
Build agent orchestration using LangChain and LangGraph.
Develop RAG pipelines using embeddings, vector search, re-ranking, and retrieval optimization.
Implement prompt engineering, tool calling, function calling, memory, and context management.
Integrate LLM agents with enterprise systems, APIs, databases, and operational tools.
Design AI solutions for network anomaly detection, investigation, and operational intelligence.
Work with structured and unstructured enterprise data.
Implement vector and search technologies such as OpenSearch, Pinecone, pgvector, and PostgreSQL.
Deploy and manage AI applications using cloud AI services.
Design scalable, secure, and production-ready AI architectures.
Evaluate and improve LLM quality, reliability, accuracy, and performance.
Provide technical leadership and guidance to engineering teams.
Work directly with client stakeholders to understand requirements and translate them into technical solutions.
Participate in architecture discussions, technical reviews, and solution demonstrations.
Required Skills
Strong hands-on experience with Python
Strong experience with Generative AI / LLM application development
Hands-on experience with LangChain
Hands-on experience with LangGraph
Strong understanding of Agentic AI
Experience building LLM agents and multi-agent systems
Strong experience with RAG architectures
Experience with embeddings, semantic search, vector search, and re-ranking
Strong prompt engineering skills
Experience with LLM tool calling and agent orchestration
Experience with vector databases and search platforms
OpenSearch
Pinecone
pgvector
PostgreSQL
Experience integrating APIs and external tools with AI agents
Cloud AI services and production deployment experience
Experience building scalable enterprise AI solutions
Strong technical leadership skills
Strong client-facing and communication skills
Preferred Skills
Telecom or network operations experience
Network anomaly detection
Network monitoring and operational intelligence
AI-driven incident investigation
Root-cause analysis
Observability or network analytics
Machine Learning / anomaly detection models
Production experience with enterprise Agentic AI solutions
Candidate Requirements
Must currently reside in the Denver, CO area
Must be available for an onsite client interview
Must be able to work onsite in Denver
Strong hands-on engineering background is required
This is a technical lead role, not a purely managerial position
Key Skills
Python, Generative AI, GenAI, LLM, Large Language Models, Agentic AI, AI Agents, LLM Agents, Multi-Agent Systems, LangChain, LangGraph, RAG, Retrieval Augmented Generation, Prompt Engineering, Tool Calling, Function Calling, Agent Orchestration, Embeddings, Vector Search, Semantic Search, Re-Ranking, OpenSearch, Pinecone, pgvector, PostgreSQL, AI ML, Machine Learning, Cloud AI, Network Anomaly Detection, Telecom, Network Operations, Operational Intelligence