Lead Python AI/LLM/RAG Engineer

About the role

Help build intelligent solutions for retail store associates.

Tasks

• Design and develop AI applications using Python, LLMs, and enterprise REST APIs.
• Build and optimize RAG pipelines, including document ingestion, embeddings, and vector search.
• Develop and deploy production-grade LLM applications and AI agents.
• Evaluate AI responses for accuracy, latency, reliability, and cost.
• Deploy, monitor, and support AI services across cloud and on-prem environments.
• Lead technical architecture, conduct code reviews, and mentor engineers.
• Collaborate with business stakeholders and maintain technical documentation.

Requirements

• 5+ years of Python development
• 3+ years of REST API development
• 2+ years of AI/ML and LLM application development
• 1+ year of hands-on RAG, embeddings, and vector database experience
• 1–2 years of agentic AI development
• 3+ years of cloud deployment experience (AWS, Azure, or GCP)
• 2+ years of technical leadership and solution architecture
• Preferred: AI workflow orchestration
• Preferred: Model fine-tuning and open-source models (PyTorch or similar)
• Preferred: AI evaluation, observability, and guardrails
• USC, EAD, or Genuine GC/H1B only
• Genuine GC and H1B candidates only.
• Candidates must be local to Charlotte, NC, or willing to relocate and work onsite from day one.

Schedule

• Hybrid – 2 days onsite
• 6-month contract (possible extension)

How to apply

• Send your resume.
• Please include your location, work authorization, and relevant experience with Python, LLMs, and RAG.

Location

• Charlotte, NC