Job Summary
We are seeking a Lead Software Engineer - Lead Python AI/LLM/RAG Engineer to design, develop, and deploy production AI solutions supporting business priorities. The role will focus on building AI applications for an AI assistant used by store associates to answer customer queries and assist with product and project sales. The ideal candidate will have strong expertise in Python, LLMs, retrieval-augmented generation (RAG), enterprise APIs, cloud deployment, and technical leadership.
Key Responsibilities
• Design and develop AI applications using Python, LLMs, and enterprise APIs.
• Build and improve RAG pipelines, including document ingestion, embeddings, and vector search.
• Evaluate AI responses for accuracy, reliability, latency, and cost, and troubleshoot issues.
• Deploy and monitor AI services in cloud and on-premises environments while maintaining security and operational stability.
• Lead technical discussions, review code, and mentor engineers on implementation.
• Collaborate with business stakeholders to clarify requirements, prioritize tasks, and demonstrate progress.
• Maintain technical documentation, deployment runbooks, and knowledge transfer materials.
• Lead technical architecture, Python development, LLM integration, API development, and retrieval-augmented generation initiatives.
• Implement automated evaluation, security controls, cloud deployment, and production monitoring for AI solutions.
Required Qualifications
• 5+ years of experience with Python development.
• 3+ years of experience building and deploying production REST APIs.
• 2+ years of experience developing LLM applications.
• 1+ year of experience building RAG pipelines involving embeddings and vector databases.
• 2+ years of experience leading solution architecture and engineering delivery.
• 3+ years of experience deploying applications on cloud infrastructure.
• 2+ years of experience in AI/ML.
• 1-2 years of experience in agentic development.
Preferred Qualifications
• Experience with AI workflow orchestration.
• Experience with model fine-tuning and open-source models using PyTorch or similar technologies.
• Experience implementing AI evaluation, observability, and guardrails.
