Description

You will design and deliver scalable, secure, and production-ready Generative AI systems on multi-cloud platforms.

This role is on-site.

Responsibilities

• Architect end-to-end Generative AI solutions, including model serving (vLLM, TGI), API integration, and user interaction layers.
• Design and implement RAG architecture using vector stores, embeddings, hybrid search, and re-ranking to embed enterprise knowledge into LLMs.
• Develop and govern Copilots in Copilot Studio, managing connectors, actions, plugins, DLP rules, and Microsoft 365 integration.
• Leverage Azure AI Foundry to operationalize LLM applications, handling prompt flow, evaluators, safety, and model orchestration.
• Implement Responsible AI, security, and HITL controls, ensuring compliance and balancing quality, latency, and cost efficiency.

Required Skills

• 8+ years of experience in cloud architecture or enterprise software engineering.
• 3+ years of hands-on experience designing or delivering Generative AI or LLM applications.
• Proven expertise with Azure AI Foundry, Azure OpenAI, and Copilot Studio (actions, connectors, governance, M365 integration).
• Experience deploying AI solutions on AWS (Bedrock, SageMaker) and/or Google Cloud Platform (Vertex AI).
• Hands-on experience with RAG, vector databases (Azure AI Search, Pinecone, OpenSearch, Vertex Matching Engine), embeddings, and hybrid search.
• Deep understanding of cloud security (IAM/RBAC, Key Vault/KMS, VPC/PrivateLink, token safety).
• Experience with Kubernetes (AKS/EKS/GKE), containerization, and API frameworks (FastAPI, Node.js, .NET).
• Proficiency in Python, TypeScript, or C#/.NET.

Preferred Skills

• Experience implementing agent-based systems using frameworks like LangChain, LlamaIndex, Semantic Kernel, or AutoGen.
• Background working with enterprise data ecosystems (Databricks, Snowflake, BigQuery, Redshift).
• Knowledge of Responsible AI frameworks, guardrails, safety filters, and evaluation methodologies.

Key Skills

Education

Any Graduate