Senior AI Engineer

Key Responsibilities

• • instrumental in architecting and deploying production-grade AI solutions using Azure OpenAI (GPT-4o), Azure Document Intelligence, and serverless computing paradigms on Microsoft Azure
  • Developing and designing solutions using Python, FastAPI, LangChain, LangGraph, Azure OpenAI (GPT-4o), Azure Document Intelligence, Azure Functions, Azure Blob Storage, Snowflake, MongoDB (Vector Search), SQL, Docker, MLflow, GitHub Actions (CI/CD), Socket.IO, Redis, and AWS SageMaker

oBackend Development

• • Build and maintain robust, production-grade backend APIs using FastAPI or Flask, ensuring secure authentication, input validation, and structured error handling.
  • Implement secure, event-driven data pipelines (e.g., Azure Functions) to automate extraction, transformation, and loading of structured and unstructured data across cloud storage and data warehouses (Azure Blob Storage, Snowflake).
  • Manage database integrations including SQL databases, Snowflake, and MongoDB (Vector Search) to support both transactional and AI-driven retrieval workflows.
  • Optimize backend systems for real-time processing of AI queries and responses, implementing asynchronous Python patterns and Redis caching to minimize latency under concurrent load.
  • Integrate real-time communication frameworks such as Socket.IO for seamless, low-latency user interactions with frontend applications (e.g., Angular, React).

2. Generative AI Model Integration

• • Utilize Azure OpenAI (GPT-4o) and related services to build LLM-powered applications, including Retrieval-Augmented Generation (RAG) systems with hybrid search (keyword + semantic).
  • Architect and orchestrate multi-agent systems using LangChain and LangGraph, designing specialized agents for tasks such as content generation, intelligent data extraction, and automated decision-making.
  • Deploy, fine-tune, and integrate AI models into business applications, working closely with product and business stakeholders to align model outputs with business objectives.
  • Optimize AI-driven prompt engineering and embedding models for efficient performance, iterating on system prompts, chunking strategies, and retrieval pipelines to maximize accuracy and reduce API costs.
  • Leverage Azure Document Intelligence for parsing unstructured documents (PDFs, earnings reports) and extracting structured financial or operational KPIs at scale.
  • Build and maintain Model Context Protocol (MCP) servers to expose internal databases and documentation to LLM clients for secure, standardized data retrieval.

3. Containerization & Deployment

• • Use Docker to containerize AI applications and their dependencies, ensuring consistent behavior across development, staging, and production environments.
  • Manage end-to-end application deployments in Azure environments (Azure Functions, Azure Workspace, Azure Blob Storage), including infrastructure setup and configuration.
  • Engineer CI/CD pipelines using GitHub Actions to automate testing, building, and deployment processes for seamless, zero-downtime releases.
  • Monitor, troubleshoot, and resolve application performance issues post-deployment using MLflow, custom dashboards, automated alerts, and logging systems.

Implement model monitoring practices to detect data drift, performance degradation, and data quality issues in production ML/AI systems.