AI Engineer – Azure AI Foundry

Experience

4 – 6 years

Level

Mid-Level

Location

Delhi / Mumbai / Bangalore (India)

Employment Type

Full-time

Primary Skills

Azure AI Foundry, RAG, AI Agents, AI / ML

Role Summary

We are looking for an AI Engineer with hands-on experience in building Generative AI solutions on Microsoft Azure. You will design and develop Retrieval-Augmented Generation (RAG) pipelines and AI agents using Azure AI Foundry, working within a team under the guidance of senior engineers and architects, and contribute to production-grade AI/ML solutions for enterprise clients.

Key Responsibilities

• Develop and deploy RAG-based applications using Azure AI Foundry, Azure OpenAI, and Azure AI Search.

• Build AI agents using Azure AI Foundry Agent Service, including tool/function calling and basic multi-step workflows.

• Implement document ingestion pipelines: parsing, chunking, embedding generation, and vector indexing.

• Write and iterate on prompts; apply prompt engineering techniques to improve answer quality and reduce hallucinations.

• Build, train, and evaluate classical ML / deep learning models for classification, forecasting, NLP, or similar use cases.

• Expose AI capabilities through REST APIs (FastAPI / Flask) and integrate them with front-end and enterprise systems.

• Run evaluation of RAG and agent outputs (groundedness, relevance, accuracy) using Azure AI Foundry evaluation tools.

• Write clean, tested, well-documented code and participate in code reviews.

• Collaborate with product owners, data engineers, and QA teams to deliver sprint commitments.

Required Skills & Experience

• 4 – 6 years of total experience in software / data / AI engineering, with at least 1.5 – 2 years in Generative AI.

• Hands-on experience with Azure AI Foundry (model catalog, deployments, prompt flow, evaluations).

• Practical experience building RAG solutions end to end (embeddings, chunking, vector search, retrieval, re-ranking basics).

• Experience building AI agents using Azure AI Foundry (Agent Service) or frameworks such as Semantic Kernel, LangChain, or AutoGen.

• Strong Python programming skills; good understanding of REST APIs and JSON.

• Working knowledge of AI/ML fundamentals: supervised / unsupervised learning, model evaluation, feature engineering, scikit-learn, and PyTorch or TensorFlow.

• Familiarity with Azure services: Azure OpenAI, Azure AI Search, Blob Storage, Azure Functions, Key Vault.

• Working knowledge of Git and CI/CD basics.

AI Engineer – Azure AI Foundry

Experience

4 – 6 years

Level

Mid-Level

Location

Delhi / Mumbai / Bangalore (India)

Employment Type

Full-time

Primary Skills

Azure AI Foundry, RAG, AI Agents, AI / ML

Role Summary

We are looking for an AI Engineer with hands-on experience in building Generative AI solutions on Microsoft Azure. You will design and develop Retrieval-Augmented Generation (RAG) pipelines and AI agents using Azure AI Foundry, working within a team under the guidance of senior engineers and architects, and contribute to production-grade AI/ML solutions for enterprise clients.

Key Responsibilities

• Develop and deploy RAG-based applications using Azure AI Foundry, Azure OpenAI, and Azure AI Search.

• Build AI agents using Azure AI Foundry Agent Service, including tool/function calling and basic multi-step workflows.

• Implement document ingestion pipelines: parsing, chunking, embedding generation, and vector indexing.

• Write and iterate on prompts; apply prompt engineering techniques to improve answer quality and reduce hallucinations.

• Build, train, and evaluate classical ML / deep learning models for classification, forecasting, NLP, or similar use cases.

• Expose AI capabilities through REST APIs (FastAPI / Flask) and integrate them with front-end and enterprise systems.

• Run evaluation of RAG and agent outputs (groundedness, relevance, accuracy) using Azure AI Foundry evaluation tools.

• Write clean, tested, well-documented code and participate in code reviews.

• Collaborate with product owners, data engineers, and QA teams to deliver sprint commitments.

Required Skills & Experience

• 4 – 6 years of total experience in software / data / AI engineering, with at least 1.5 – 2 years in Generative AI.

• Hands-on experience with Azure AI Foundry (model catalog, deployments, prompt flow, evaluations).

• Practical experience building RAG solutions end to end (embeddings, chunking, vector search, retrieval, re-ranking basics).

• Experience building AI agents using Azure AI Foundry (Agent Service) or frameworks such as Semantic Kernel, LangChain, or AutoGen.

• Strong Python programming skills; good understanding of REST APIs and JSON.

• Working knowledge of AI/ML fundamentals: supervised / unsupervised learning, model evaluation, feature engineering, scikit-learn, and PyTorch or TensorFlow.

• Familiarity with Azure services: Azure OpenAI, Azure AI Search, Blob Storage, Azure Functions, Key Vault.

• Working knowledge of Git and CI/CD basics.

Introduction:

The AI Workforce Endpoint Technical Lead is a senior technical leadership role responsible for architecting and delivering enterprise endpoint solutions across Microsoft Intune, Windows Autopilot, Windows 365, Azure Virtual Desktop, and related Microsoft technologies. This role provides technical direction for large-scale endpoint transformation programs, ensuring successful delivery, operational excellence, and adherence to architecture, security, and quality standards throughout the project lifecycle. 

Come Join Us: 

This is an opportunity to lead the delivery of complex endpoint transformation programs for large enterprise customers. You will apply deep technical expertise across modern device management technologies while guiding delivery teams, solving complex technical challenges, and ensuring successful outcomes across endpoint deployments, security initiatives, virtualization platforms, and operational modernization efforts. 

What you'll do: 

Endpoint Architecture & Delivery Leadership 

• Lead the architecture and delivery of enterprise endpoint solutions across Microsoft Intune, Windows Autopilot, Windows 365, Azure Virtual Desktop, and mobile device management platforms. 

• Serve as the primary technical authority for endpoint transformation programs from planning through deployment and stabilization. 

• Define and maintain technical standards, implementation patterns, reference architectures, and deployment methodologies. 

• Oversee technical governance, risk management, and quality assurance across endpoint delivery programs. 

• Provide architectural guidance for endpoint security, compliance, identity integration, application delivery, and device lifecycle management. 

• Act as the senior escalation point for complex technical issues and deployment challenges. 

Endpoint Engineering & Automation 

• Design and implement automation solutions that improve device provisioning, application deployment, compliance management, reporting, and operational support. 

• Integrate endpoint management platforms with Microsoft 365, Entra ID, PowerShell automation, Power Platform, and operational tooling. 

• Develop reusable deployment assets, engineering standards, and accelerators that improve delivery quality and consistency. 

• Drive continuous improvement through Endpoint Analytics, operational reporting, platform optimization, and automation. 

Program Delivery & Technical Governance 

• Lead technical workstreams across large endpoint transformation and modernization programs. 

• Ensure adherence to architecture standards, security baselines, deployment controls, and operational best practices. 

• Conduct architecture reviews, deployment readiness assessments, technical quality reviews, configuration audits, and risk assessments. 

• Coordinate with project managers, engineering teams, security stakeholders, infrastructure teams, and client IT teams to remove delivery blockers and maintain program momentum. 

• Support transition activities including operational readiness, knowledge transfer, documentation, stabilization, and support handoff. 

Stakeholder & Client Leadership 

• Act as a trusted technical advisor to client stakeholders throughout the delivery lifecycle. 

• Translate complex endpoint requirements and technical risks into clear decisions and actionable delivery plans. 

• Lead client-facing technical workshops, architecture reviews, program checkpoints, and executive-level delivery briefings. 

• Build productive working relationships across client technology, security, operations, and business teams. 

Team Leadership & Capability Development 

• Mentor endpoint engineers and architects in delivery methodologies, engineering practices, and Microsoft endpoint technologies. 

• Build technical capability through coaching, peer reviews, technical communities, and knowledge-sharing activities. 

• Contribute to internal standards, reference architectures, automation frameworks, delivery playbooks, and reusable assets. 

Job Family Overview:

Focus on (Cloud and On-Premise) deployments of Dynamics 365, including all related configurations, Azure DevOps setup, Azure services configuration and environment monitoring and maintenance.

Job Overview:

Responsible for designing and implementing AX systems and cloud infrastructure, operating systems, networking, security and systems management architectures/solutions that enable effective client operations and collaboration.​

Key Accountabilities:

• Creation of build automation and/or build guides for solid, repeatable server builds and deployments
• Deploy enterprise-wide messaging and collaboration solutions to lower administrative costs and enhance end-user productivity
• Collect, identify, define and organize detailed user and systems requirements. Coordinate and collaborate with others to ensure plans and identified solutions meet the customer needs and expectations
• Monitor performance and analyze statistics to identify and resolve system problems
• Establish and maintain security including AX Security, integrity and business continuity controls and documents
• Responsible for the design of the AX technical infrastructure and integration in Customer existing environment
• works with Customer IT Operation management
• Designs performance framework and high availability architecture, designs and run performance benchmarks on critical business transactions

Key Role Skill & Capability Requirements:

Global skill requirements to come; speak to hiring manages, capability leads, and region Talent Community champions for needs in local market.

Preferred Certifications:Preferrred Education Background:

You will likely posess a Bachelor's degree or equivalent in relevt field.

Preferred Years of Work Experience:

3-4 years of relevant experience.

Preferred Years of Management Experience:Scope of Work:

Nature of Work: Executes project/program plans and processes in alignment with established operational objectives.Scope of Work: Work must be coordinated across different workstreams, processes, or projects.Complexity: Complex problems that can span across work domains requiring considerable judgement of contextual factors.Discretion: Wide latitude in approach to work within established work plans.Organizational Impact: Work efforts have an immediate impact on Avanade and/or client operations. If client-facing, should start to support client relationship and sales outcomes.Supervision Received: Works under general guidance and direction, but fully independent in own work with latitude for autonomous decision-making related to work process.Supervision Provided: Supports more junior colleagues on work efforts, with routine supervision of work efforts. May serve as Career Advisor.Knowledge Applied: Applies advanced knowledge of a learned occupation / discipline and basic knowledge of business operations.

Key Performance Indicators:Relevant Additional Details:

This field is reserved for any additional details that may not be globally relevant and consistently vary on a position-by-position basis.