Python Developer – AI Systems, LLMs & RAG

Role Overview

We are seeking an experienced Python Developer capable of building intelligent, data-driven applications that power next-generation LLM and RAG-based AI systems. The ideal candidate will possess strong backend development skills and hands-on exposure to AI model integration, vector databases, and agentic pipelines.

Key Responsibilities

• Design, build, and optimize Python-based AI applications leveraging LLMs and RAG for enterprise use cases.
• Develop and deploy custom LLM pipelines, including data preprocessing, model fine-tuning, and inference optimization.
• Implement retrieval-augmented generation workflows integrating embedding generators, retrievers, and contextual generators.
• Engineer robust LangChain, LlamaIndex, or Haystack applications with database and API integrations.
• Build and maintain tool-enabled AI agents capable of reasoning and autonomous task execution (CrewAI, LangGraph, AutoGPT).
• Develop modularized APIs and microservices for internal and client-facing AI features.
• Collaborate closely with ML and data teams on cloud deployment, scalability, and model monitoring (AWS Sagemaker, Azure ML).
• Apply prompt engineering principles to optimize LLM outputs for reliability, contextual accuracy, and performance.
• Maintain and document AI system architectures, data workflows, and integration dependencies.

Required Skills & Experience

• 3+ years of Python development experience with a focus on backend or AI systems.
• Strong knowledge of REST API design, asynchronous frameworks (FastAPI, Flask), and modular architecture.
• Hands-on experience with LLM integration using OpenAI, HuggingFace Transformers, or Anthropic SDKs.
• Familiarity with vector databases (Pinecone, FAISS, Weaviate, Qdrant).
• Experience with LangChain, LlamaIndex, or comparable orchestration frameworks for retrieval and agentic AI design.
• Understanding of prompt engineering techniques (few-shot prompting, chain-of-thought, context-grounded prompts).
• Experience building and consuming cloud-based machine learning endpoints.
• Proficiency with SQL/NoSQL databases for metadata storage and embedding management.
• Strong debugging and performance profiling skills for production-grade systems.

Preferred Qualifications

• Experience developing multi-agent architectures or tool-augmented reasoning frameworks.
• Familiarity with LLM fine-tuning or PEFT methods (LoRA, QLoRA).
• Exposure to AI observability and monitoring tools like LangFuse, Phoenix, or Traceloop.
• Prior experience in healthcare data systems or Revenue Cycle Management.