Azure AI Engineer

Tata Consultancy Services Limited; India; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Tata Consultancy Services Limited in India seeks an experienced AI/ML developer to design and deploy cloud-native AI solutions on Azure. You will build backend microservices, integrate LLMs, and optimize performance and cost in production.

The role requires hands-on Python/C#, expertise in Azure OpenAI and Document Intelligence, and a focus on responsible AI and secure deployment across Azure services. Collaborate with stakeholders, document architectures, and stay current with Azure innovations

Qualifications

• Experience in software engineering or AI/ML development with Azure cloud services.
• Hands-on Python for backend and AI workflows.
• Experience with Azure AI Document Intelligence (OCR, forms, extraction).
• Deep knowledge of Azure OpenAI and GPT models, embeddings, and prompt engineering.
• Experience deploying in cloud-native Azure environments and using Azure Functions, APIM, Resource Groups, Storage, App Insights, App Service, Key Vault.
• Experience calling LLM APIs and integrating into applications.
• Knowledge of vector stores and retrieval with LLMs (RAG).
• Strong Python or C# coding skills for microservices.
• Familiarity with Azure DevOps, CI/CD, IaC, and deployment automation.
• Strong analytical, communication, and stakeholder management skills.

Responsibilities

• Design, develop, and deploy AI solutions using Azure AI Document Intelligence, Azure OpenAI, and Azure Foundry.
• Build and operationalize LLM-based applications including prompt engineering and embeddings.
• Develop intelligent document processing pipelines for classification, extraction, OCR, and workflows.
• Implement RAG architectures using Azure Cognitive Search or vector databases for retrieval and citation-based responses.
• Integrate LLM capabilities with enterprise systems using REST APIs, Azure Functions, APIM, Logic Apps, or Power Platform.
• Build cloud-native AI services using Azure Functions, Resource Groups, App Services, Storage, App Insights, Key Vault.
• Maintain clean, secure Python or C# code following best practices.
• Ensure security, governance, and compliance in deployments.
• Monitor model performance and optimize latency/cost.
• Collaborate with stakeholders to define architectures and measure AI outcomes.
• Produce architecture runbooks and technical docs.
• Stay updated with Azure AI capabilities and enterprise AI tooling.

Skills

Azure AI services

Python

Azure OpenAI

Azure Document Intelligence

LLM integrations

Azure Foundry

Azure Functions

APIM

Vector databases

RAG architectures

Python or C#

CI/CD automation

Security & compliance

Debugging & optimization

Azure DevOps

Tools

Azure Cosmos DB

LangChain

Semantic Kernel

Job description

JOB DESCRIPTION

Must Have Skills:

• Experience in software engineering or AI/ML development, with at least 4+ years working with Azure AI services.
• Strong hands-on experience with Python for backend development, AI pipelines, and LLM integrations.
• Strong hands-on experience with Azure AI Document Intelligence including extraction, forms, OCR, and classification.
• Deep understanding of Azure OpenAI, including GPT models, embeddings, chat completions, prompt engineering, and content safety.
• Practical experience using Azure AI Foundry for building, testing, and operationalizing AI apps.
• Experience building AI solutions in cloud-native Azure environments including: Azure Functions, Azure API Management (APIM), Azure Resource Groups, Azure Storage Accounts, App Insights, Azure App Service, Azure Key Vault
• Hands-on experience making calls to LLM APIs (chat completions, embeddings, model inference endpoints) and integrating them into applications.
• Experience architecting and implementing RAG systems using Azure Cognitive Search or vector index stores.
• Strong programming experience in Python or C# (Node.js acceptable) for backend microservices and integrations.
• Practical experience with Azure services including Logic Apps, Event Grid, Storage, Functions, and automated workflows.
• Solid knowledge of Responsible AI, privacy, compliance, and secure deployment models.
• Strong debugging and optimization skills for AI workloads (cost, latency, throughput).
• Hands-on experience with Azure DevOps, Git repositories, CI/CD pipelines, IaC, and deployment automation.
• Strong analytical, communication, and stakeholder management skills.

Desirable Skills / Knowledge / Experience:

• Experience using vector databases such as Azure Cosmos DB with vector indexing, Redis Enterprise, or Pinecone.
• Familiarity with multi-agent AI architectures, orchestration frameworks, and agentic workflows.
• Exposure to Power Platform AI Builder and low-code AI integrations.
• Understanding of NLP techniques including entity extraction, embeddings, semantic search, text analytics, and conversation design.
• Experience with frameworks like LangChain, Semantic Kernel, or LlamaIndex.

Responsibilities or Expectations from the Role:

• Design, develop, and deploy AI solutions using Azure AI Document Intelligence, Azure OpenAI, and Azure AI Foundry.
• Build and operationalize LLMbased applications, including prompt engineering, context engineering, embeddings, chat completions, and grounding strategies.
• Develop intelligent document processing pipelines using Azure AI Doc Intelligence for document classification, extraction, OCR, and automated workflows.
• Implement RAG architectures using Azure Cognitive Search or vector databases for retrieval grounding, chunking, ranking, and citationbased responses.
• Integrate LLM and AI capabilities with enterprise systems using REST APIs, Azure Functions, APIM, Logic Apps, or Power Platform.
• Build cloud-native AI services using Azure Functions, Azure Resource Groups, App Services, Storage Accounts, App Insights, and Key Vault.
• Develop and maintain clean, secure, and well-tested Python or C# code following engineering best practices.
• Ensure adherence to security, governance, and compliance standards including encryption, responsible AI, and regulated-industry policies.
• Monitor AI model performance and system behavior, optimize response quality, troubleshoot issues, and reduce operational bottlenecks.
• Collaborate with stakeholders to identify use cases, define architectures, and deliver measurable AI outcomes.
• Produce solution documents, system diagrams, runbooks, and technical knowledge-base content.
• Stay current with emerging Azure AI ecosystem capabilities, LLM advancements, and enterprise AI tooling.