AI Infrastructure Architect

Intro: Accenture is hiring an AI Infrastructure Architect (AI LLM Technology Architecture Team Lead/Consultant) to architect and build custom AI infrastructure and hardware solutions and to implement production-grade LLM/GenAI components. This is a full-time, Chennai-based engineering role requiring a minimum of 5 years' experience and 15 years of full-time education. Role purpose and main responsibilities: - Architect and build AI infrastructure/hardware solutions focused on performance, power, cost and scalability of the computational stack. - Translate high-level architectures into production-quality components on Azure, owning platform-specific engineering for LLM-driven applications, RAG pipelines, multi-agent workflows and AI platform integrations. - Design and build LLM application components including prompts, tools, agents, orchestration flows, memory/context handling, retrieval pipelines and evaluation harnesses. - Implement data ingestion, parsing, chunking, enrichment, embeddings, vector search and retrieval workflows for structured and unstructured enterprise content. - Create Foundry-based agents, integrate Azure AI Search for RAG, and implement secure API/tool calls via API Management, Logic Apps and Functions. - Engineer safety and control components (PII detection/redaction, prompt-injection defenses, content filters, guardrails, authentication/authorization, lineage and audit logging). - Collaborate with architects, data engineers, product owners and security stakeholders; maintain technical artifacts such as integration specs, deployment runbooks and evaluation results. Required qualifications and experience: - Bachelor’s degree in Computer Science, Computer Engineering, Data Science, AI/ML, IT or related engineering discipline. - Minimum 5 years' experience (job lists 5–10 years); hands-on coding in Python; understanding of APIs, distributed systems, CI/CD, testing, observability and secure SDLC practices. - Experience delivering AI/ML or data products in at least one industry domain (banking, insurance, healthcare, public sector, retail or energy). Technical environment and tools (required): - Microsoft Foundry / Azure AI Foundry, Foundry Agent Service, Azure OpenAI models, Azure AI Search, Prompt Flow, Azure Functions, Logic Apps, API Management, Event Grid, Microsoft Fabric, Entra ID, Key Vault, Azure Monitor, Application Insights. - LLM architecture patterns including RAG, function/tool calling, agent orchestration, prompt engineering, embeddings, vector DBs and evaluation metrics. - Git-based development, automated testing, CI/CD, infrastructure-as-code, containerization and orchestration practices. Preferred / Good-to-have: - Azure AI Engineer, Azure Solutions Architect or Azure Developer certifications; exposure to Semantic Kernel, private networking, Defender for Cloud and enterprise Responsible AI governance. - Familiarity with open-source frameworks: LangChain, LangGraph, LlamaIndex, Haystack, MLflow, FastAPI, Docker, Kubernetes. - Experience with Responsible AI practices, model risk management, synthetic data generation, human-in-the-loop review, A/B testing and GenAI cost optimization.