2 days ago
Bengaluru, IndiaStaff+
Responsibilities
- Lead discovery and architecture workshops and translate business objectives into enterprise AI roadmaps, delivery scopes, architectures, estimates, risks, and success criteria.
- Design end-to-end architectures for Gemini Enterprise, enterprise search, connectors, retrieval services, custom agents, APIs, integration services, models, and tools.
- Define enterprise knowledge, ingestion, metadata, indexing, synchronization, retrieval, access-control, taxonomy, ontology, and knowledge-graph architectures.
- Design retrieval-augmented generation, semantic search, hybrid search, embeddings, reranking, grounding, contextual retrieval, and source-attribution patterns.
- Design secure AI agents and multi-agent solutions with orchestration, tool/function calling, memory, planning, approvals, and human-in-the-loop controls.
- Establish responsible AI, security, privacy, compliance, risk, auditability, prompt-security, data-protection, and agent-governance frameworks.
- Define evaluation, production acceptance, scalability, performance, observability, cost, operational-readiness, and monitoring standards.
- Implement LLMOps practices covering evaluation, testing, prompt and model lifecycle management, release governance, and production monitoring.
- Lead and mentor engineering teams and provide hands-on technical leadership through design, code, security, infrastructure, and deployment reviews.
- Lead client architecture discussions and contribute to pre-sales, proposals, estimations, demonstrations, solution shaping, and architecture presentations.
Requirements
- At least 15 years of experience in Large Language Models (LLMs).
- 12 to 18 years of overall experience in enterprise technology delivery.
- At least 5 years of experience in cloud solution or enterprise architecture.
- Strong Google Cloud architecture experience with practical exposure to Gemini, Vertex AI, or equivalent enterprise AI capabilities.
- Experience designing enterprise search, knowledge-assistant, retrieval, grounding, and agentic AI solutions.
- Strong enterprise architecture expertise across application, integration, data, security, identity, cloud, and AI domains.
- Experience integrating enterprise platforms and data sources using APIs, connectors, event-driven architectures, data pipelines, and custom services.
- Understanding of prompt engineering, context management, model limitations, hallucination risks, evaluation approaches, and AI safety controls.
- Preferred experience with AI agent implementation, multi-agent orchestration, MCP, A2A, ADK, enterprise search, knowledge management, taxonomy, ontology, knowledge graphs, and Responsible AI frameworks.
- Experience with enterprise AI ecosystems such as Microsoft Copilot, Azure AI, Amazon Q, OpenAI, and Anthropic is preferred; relevant cloud or AI certifications are also preferred.
Benefits
- The position is based at the Bengaluru office.
Tech Stack
Google Cloud
Categories
About Accenture
Accenture is a global professional services firm providing management consulting, systems integration and technology, cybersecurity, and business process outsourcing for enterprises and governments. It operates a services-driven model delivering projects and managed services, often with major cloud and software partners, across industries worldwide. Headquartered in Dublin and publicly traded on the NYSE (ACN), it originated as Andersen Consulting and adopted the Accenture name in 2001.