EDS Supervising Associate GEN AI

AI Engineer / Cloud Solutions Architect / LLM & Automation Specialist

Overview

Were seeking an experienced AI Engineer / Cloud Solutions Architect / LLM & Automation Specialist with 810 years of overall IT experience including 5 years in AI/ML and 3 years in GenAI & LLM-based system development.

This role is ideal for someone who thrives at the intersection of AI innovation cloud architecture and intelligent automation and is passionate about bringing cutting-edge AI solutions into real-world enterprise environments.

As part of our advanced engineering team you will design architect and deliver scalable AI agents multi-agent systems automation frameworks and cloud-native AI applications that drive measurable business impact.

Key Responsibilities

AI & LLM Engineering

• Architect develop and deploy intelligent solutions using Large Language Models (LLMs) including Azure OpenAI Google Gemini and custom fine tuned models.
• Build production-grade AI agents multi-agent orchestrations and intelligent tool-augmented workflows.
• Develop context-aware pipelines using frameworks such as LangChain LangGraph Autogen CrewAI and Model Context Protocol (MCP).
• Design prompt engineering strategies retrieval-augmented generation (RAG) vector search and LLM evaluation frameworks.

Cloud Architecture & Engineering

• Architect cloud-native AI deployments on Azure (Functions App Service Kubernetes Databricks SQL DevOps CI/CD).
• Design scalable secure and cost-optimized cloud solutions aligned with enterprise standards.
• Build containerized AI services using Docker Kubernetes/KaaS and distributed compute environments.
• Collaborate with security and infrastructure teams to integrate AI solutions with identity access and governance requirements.

Automation & Workflow Orchestration

• Build intelligent workflows and prototypes using Microsoft Copilot Studio Streamlit and other low code environments.
• Integrate LLM capabilities into business processes enterprise applications and data pipelines.

End-to-End Delivery

• Drive AI solution lifecycle from experimentation PoC MVP through production hardening and monitoring.
• Perform model evaluations feasibility studies scalability planning and cost estimation.
• Work cross-functionally with product engineering and business stakeholders to translate problems into intelligent solutions.
• Mentor teams and contribute to AI best practices architecture patterns and reusable components.

Core Skills & Technical Expertise

AI ML & GenAI

• 5 years experience in AI/ML including NLP deep learning embeddings model tuning.
• 3 years hands on experience with GenAI & LLM ecosystems.

Expertise in:

• Azure OpenAI (GPT 4 GPT 4o custom models)
• Google Gemini Claude (optional exposure)
• LangChain LangGraph Autogen CrewAI MCP
• RAG pipelines vector stores (FAISS Chroma Azure AI Search)

Programming & Prototyping

• Strong expertise in Python (core libraries async programming API integration).
• Fast prototyping using Streamlit Microsoft Copilot Studio AI Foundry and REST API frameworks.

Cloud & DevOps

• Deep knowledge of Azure services: Functions App Services DevOps Kubernetes Databricks Key Vault Storage.
• Experience deploying scalable AI microservices containerized apps and secure API endpoints.
• Understanding of MLOps/AIOps frameworks CI/CD pipelines and observability patterns.

Automation & Integration

• Experience building agentic workflows orchestration frameworks and enterprise automation systems.
• Ability to integrate AI with enterprise apps databases APIs and business workflows.

Preferred Qualifications

• Bachelors or masters degree in computer science Engineering AI or related field.
• Certifications in Azure or equivalent cloud/AI credentials.
• Experience with multi-agent system design retrieval frameworks and enterprise RAG.
• Exposure to security governance and responsible AI practices.