• Application Development: Design and develop robust backend services using Python (FastAPI, Flask, or Django) to power LLM-based enterprise features.
• LLM Integration: Implement and optimize LLM workflows, like agentic reasoning, and complex chain-of-thought processing, Retrieval-Augmented Generation (RAG) etc.
• Data Engineering: Build efficient data ingestion pipelines to process, chunk, and embed enterprise data into vector databases.
• System Reliability: Implement rigorous monitoring for LLM outputs to track latency, costs, and response quality (detecting hallucinations or bias).
• API Mastery: Architect and maintain secure, well-documented RESTful or GraphQL APIs that interface with both internal services and external AI providers.
• Technical Mentorship: Contribute to architectural discussions and provide guidance to mid-level engineers through code reviews and technical documentation.

‍

• Python Expertise: 5–8 years of professional experience in Python, with deep knowledge of asynchronous programming, testing frameworks (Pytest), and performance optimization.
• AI Tooling: Hands-on experience with LLM orchestration frameworks such as LangChain, LlamaIndex, or LangGraph.
• Vector Infrastructure: Proficiency in working with vector stores (e.g., Pinecone, Weaviate, Milvus, or pgvector) and understanding of embedding models.
• Database Knowledge: Strong experience with relational databases (PostgreSQL/MySQL) and NoSQL solutions (Redis, MongoDB).
• Cloud & Containers: Experience deploying and scaling Python applications in cloud environments (AWS, Azure, or GCP) using Docker and Kubernetes.
• Software Design: Solid understanding of design patterns, microservices architecture, and clean code principles in an enterprise context.

‍