Lead Python AI/LLM/RAG Engineer

Required Skills (top 3 non-negotiables):

5+ years of Python and 3+ years building production REST APIs.

2+ years developing LLM applications, including 1+ year with RAG, embeddings, and vector databases.

2+ years leading solution architecture and engineering delivery, plus 3+ years deploying applications on cloud infra

Day to Day 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; troubleshoot issues.

Deploy and monitor AI services in the cloud and onprem, 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.

Additional Skill

Python & API Development: 5+ years Python; 3+ years REST APIs.

Agentic Development - 1 to 2 years

AI/ML & Generative AI: 2+ years AI/ML; 2+ years LLM applications.

RAG & Vector Databases: 1+ year building retrieval and embedding pipelines.

Cloud & Deployment: 3+ years

Technical Leadership & Architecture: 2+ years leading engineering delivery and solution design.

Preferred Skills (nice to have)

Experience with AI workflow orchestration

Model fine-tuning and open-source model experience using PyTorch or similar technologies

AI evaluation, observability, and guardrails implementation.