AI Delivery Lead

Accenture PLC; Dubai; On-site; AED 900,000 - 1,350,000; Full time

Job summary

Avanade seeks an experienced Generative AI / Azure AI Engineering Lead in Dubai to architect, develop, and deploy enterprise AI solutions on Microsoft Azure. You will lead architecture, design, and delivery of AI platforms, enabling document understanding, RAG-based apps, and agentic workflows with robust governance, citation grounding, and scalable cloud-native patterns.

The role requires hands-on expertise in Azure OpenAI, Foundry, AI Search, storage services, and ML tooling, plus strong

Qualifications

• Extensive experience with Generative AI & LLM engineering in Azure.
• Hands-on with RAG pipelines, multi‑agent workflows, and document intelligence.
• Strong knowledge of prompt engineering, grounding, and citation strategies.
• Proficient in Python, orchestration pipelines, and API-driven integrations.

Responsibilities

• Lead architecture, design, and delivery of enterprise Generative AI solutions on Azure.
• Develop AI applications using Azure OpenAI, Foundry, AI Search and ML services.
• Build end-to-end RAG and multi-agent systems with deterministic logic and citations.
• Collaborate with stakeholders to translate business needs into scalable AI architectures.
• Deliver client-facing walkthroughs, documentation, and implementation roadmaps.

Skills

Azure OpenAI

LLM orchestration

Prompt engineering

Agentic AI

Python

Tools

LangChain

LlamaIndex

Promptflow

FastAPI

REST APIs

Git

Docker

Azure Functions

Azure Blob Storage

Job description

Role Overview

We are looking for an experienced Generative AI / Azure AI Engineering Lead with 11+ years of experience in IT, AI Engineering, Machine Learning, Generative AI, and cloud-based AI solution delivery. The candidate will be responsible for designing, developing, and deploying enterprise-grade AI solutions using Azure OpenAI, Microsoft Foundry / Azure AI Foundry, Azure AI Search, RAG, Agentic AI, Python, LangChain, Azure Functions, and cloud-native Azure services. The role requires strong hands‑on expertise in building production‑ready Generative AI platforms involving retrieval-augmented generation, enterprise knowledge search, document intelligence, multi‑agent workflows, structured AI outputs, evidence‑based citations, workflow automation, and API‑driven integrations. The candidate should be capable of converting complex business requirements into scalable AI architectures, leading technical teams, defining solution blueprints, and delivering client‑facing AI solutions for enterprise stakeholders.

Key Responsibilities

Lead the architecture, design, development, and implementation of enterprise Generative AI solutions on Microsoft Azure. Design and develop AI applications using Azure OpenAI, Microsoft Foundry / Azure AI Foundry, Azure AI Search, Azure Functions, Azure Blob Storage, Azure Content Understanding, and Azure Machine Learning. Build end‑to‑end RAG‑based applications using document ingestion, chunking, embeddings, vector search, hybrid search, semantic ranking, metadata filtering, and citation‑grounded response generation. Design and implement Agentic AI and multi‑agent architectures using orchestrator agents, specialist agents, tool‑based workflows, system prompts, structured prompts, and deterministic business logic. Integrate Azure OpenAI models with enterprise applications for document summarization, knowledge retrieval, intelligent Q&A, business decision support, content generation, and workflow automation. Develop Python‑based orchestration pipelines for agent execution, business rule processing, scoring logic, evidence mapping, structured JSON response generation, exception handling, and API integration. Implement document intelligence workflows using OCR, text extraction, metadata enrichment, prebuilt/custom analyzers, content chunking, embedding generation, and vector indexing pipelines. Configure and optimize Azure AI Search indexes for vector retrieval, keyword search, hybrid search, semantic search, filtering, ranking, and source traceability. Design secure and scalable cloud‑native AI solutions using Managed Identity, Azure AD / Entra ID, Azure Key Vault, RBAC, API security, logging, and monitoring. Collaborate with business stakeholders, product owners, architects, data engineers, application teams, and client teams to translate business requirements into scalable AI solution designs. Define solution architecture, integration patterns, data flow, security model, deployment approach, and implementation roadmap for Generative AI solutions. Ensure AI responses are reliable, traceable, and business‑ready through prompt engineering, grounding, hallucination control, citation validation, structured output design, and evaluation frameworks. Lead technical teams across design, development, testing, debugging, deployment, production readiness, and support activities. Troubleshoot and optimize AI pipelines related to retrieval quality, prompt accuracy, model performance, token usage, vector indexing, search relevance, latency, and response reliability. Prepare technical documentation, architecture diagrams, implementation plans, proof‑of‑concepts, client‑facing walkthroughs, and solution presentations.

Required Skills

Generative AI & LLM Engineering Strong experience with Azure OpenAI, GPT models, LLM orchestration, prompt engineering, system prompts, function calling, structured output generation, and LLM‑based application development. Hands‑on experience in building RAG pipelines, Agentic AI workflows, multi‑agent architectures, and enterprise chatbot solutions. Strong understanding of hallucination control, citation grounding, AI safety guardrails, model evaluation, response validation, and prompt optimization.

Azure AI & Cloud Services Strong hands‑on experience with Microsoft Foundry / Azure AI Foundry, Foundry Agents, Azure OpenAI Service, Azure AI Search, Azure Content Understanding, Azure Machine Learning, Azure Functions, Azure Blob Storage, Azure Key Vault, Azure Monitor, and Application Insights. Experience in designing cloud‑native AI solutions with Managed Identity, Azure AD / Entra ID, RBAC, secure API access, logging, monitoring, and enterprise‑grade access control.

RAG & Enterprise Knowledge Search Experience in designing and implementing document ingestion pipelines, chunking strategies, embedding generation, vector indexing, vector search, hybrid search, semantic ranking, metadata filtering, and ACL‑based retrieval. Strong understanding of SharePoint integration, enterprise content grounding, source traceability, document versioning, citation generation, and evidence‑based AI responses.

Programming & Frameworks Strong programming experience in Python. Hands‑on experience with FastAPI, LangChain, LlamaIndex, Promptflow, REST APIs, JSON schema design, SQL, PostgreSQL, Supabase, Git, CI/CD, Docker, and Azure Container Apps. Ability to design backend services, orchestration layers, reusable AI components, and API‑driven integrations.

Machine Learning & NLP Strong understanding of Machine Learning, NLP, text classification, named entity recognition, semantic similarity, document classification, OCR pipelines, embeddings, and model deployment. Experience with ML/NLP techniques and models such as BERT, Word2Vec, TF‑IDF, LSTM, RNN, XGBoost, supervised learning, and MLOps practices.

Preferred Experience

Experience in enterprise domains such as government, ports and logistics, KYC, compliance, legal, finance, procurement, enterprise knowledge management, or customer service automation. Experience with document intelligence, video RAG, SharePoint‑based knowledge retrieval, Microsoft Teams agents, and enterprise chatbot platforms. Experience in designing AI systems that require structured JSON outputs, scoring logic, decision support, risk assessment, evidence mapping, and source‑level traceability. Experience with Snowflake, PostgreSQL, Supabase, Cosmos DB, Azure Blob Storage, and external API integrations. Experience with production‑readiness activities including testing, monitoring, telemetry, logging, performance tuning, and AI response evaluation.

Tools & Technologies

Cloud & AI Microsoft Foundry / Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Machine Learning, Azure Content Understanding, Azure Functions, Azure Blob Storage, Azure Key Vault, Azure Monitor, Application Insights Frameworks LangChain, LlamaIndex, Promptflow, FastAPI Programming Python, SQL, REST APIs, JSON, Git Data & Storage PostgreSQL, Supabase, Snowflake, Cosmos DB, Azure Blob Storage AI/ML RAG, LLMs, embeddings, vector search, NLP, BERT, LSTM, XGBoost, OCR, NER Security Azure AD / Entra ID, Managed Identity, RBAC, ACL‑based retrieval, API security DevOps Git, CI/CD, Docker, Azure Container Apps, logging, monitoring, and deployment automation

Expected Outcomes

Deliver scalable, secure, and production‑ready Generative AI solutions on Microsoft Azure. Build reliable RAG and Agentic AI applications with strong grounding, citation traceability, and hallucination control. Design enterprise‑grade AI architectures that integrate with business systems, document repositories, databases, APIs, and cloud services. Lead technical delivery from solution design to implementation, testing, deployment, and production support. Support client‑facing discussions, demos, technical walkthroughs, solution documentation, and delivery planning.

About Us

At Avanade, we advance the world through the power of people and Microsoft. Join us to shape your skills and the future with bold ideas and innovative solutions. Our partnership with Microsoft and Accenture empowers you to unlock your full potential. Working at Avanade offers the chance to build a career path that suits your skills and interests and the freedom to be your authentic self. We are committed to your growth, well‑being, and success. This is where passion meets opportunity, technology meets humanity, and every challenge is a chance to make a genuine impact on colleagues, clients, and communities. Together, we do what matters.