Backend Python Developer - Hybrid (Full-Time)

We are looking for a talented Sr. Backend Python Developer to strengthen the Generative AI
engineering team. You will focus on developing secure, scalable, and efficient servicesfor the AI platform. You'll contribute to building APIs, vector database integration, andLLM orchestration pipelines that drive real-time document understanding and AI-driveninsights.

Responsibilities

• Design, develop, and optimize RESTful and streaming APIs using FastAPI and
  Python.
• Architect scalable and modular microservices, integrating with vector databases
  such as Azure AI Search, AstraDB, or FAISS.
• Implement Retrieval-Augmented Generation (RAG) pipelines and intelligent
  document ingestion workflows.
• Build backend services supporting AI chatbot functionality, including prompt
  orchestration, real-time LLM responses, and streamed chat experiences.
• Manage user access control, chat history, token usage tracking, and
  metadata services for documents.
• Apply software engineering best practices including Design Patterns (e.g.,
  Singleton, Factory) and clean architecture principles.
• Leverage SQLAlchemy ORM for database modeling and asynchronous I/O for
  scalable performance.
• Ensure secure coding practices, observability, and robust error handling.
• Work on API Gateway design and implementation for managing authentication,
  rate limiting, and routing.
• Deploy and manage services using Docker, Kubernetes, and cloud
  infrastructure on Azure or equivalent (AWS/GCP).
• Integrate and operationalize Azure AI Services (e.g., OpenAI, Azure Search,
  Cognitive Services) or comparable cloud-based AI tools.

Qualifications

• 5+ years (5 min to 8 max years)of experience in Python backend
  development, with a strong understanding of asynchronous programming.
• Expertise in FastAPI, SQLAlchemy, Pydantic, and scalable backend
  architecture.
• Hands-on experience with chatbot development and integrating LLMs (e.g.,
  GPT, Claude, Gemini) into backend systems.
• Familiarity with LLM orchestration frameworks such as LangChain, OpenAI
  SDK, or LlamaIndex.
• Strong knowledge of RAG architecture and real-time document-query pipelines.
• Experience with API Gateway management and building secure, multi-tenant
  backend platforms.
• Proficiency in SQL/NoSQL databases such as Postgre SQL,MYSQL or
  CosmosDB.
• Experience integrating Azure AI Services, or equivalents from AWS or Google
  Cloud.
• Understanding of role-based access control and secure authentication using
  JWT/OAuth2.
• Familiarity with containerization (Docker), CI/CD workflows, and
  monitoring/logging tools.
• Hands on with frontend technologies such as Next.js, React.js, TypeScript,
  and Tailwind CSS to enable better cross-functional collaboration.
• Understanding of frontend-backend integration, chat UI streaming, and
  WebSockets/SSE mechanisms.
• Exposure to document processing, chat memory management, and multi-
  agent prompt routing.
• Contributions to open-source Generative AI tools, AI agents, or internal LLM
  platforms.
• Experience working in Agile teams, writing unit/integration tests, and participating
  in code reviews.