AI Architect/Delivery Lead - Agentic AI & GenAI Systems

Description :

Experience : 6 to 12 Years

Location : Bengaluru / Hyderabad / Delhi NCR

Work Mode : Hybrid

Employment Type : Full-time

About the Role :

We are looking for an experienced AI Architect / Delivery Lead to drive the architecture, design, and end-to-end delivery of enterprise-scale Agentic AI and Generative AI systems. This role is suited for someone who can combine deep technical expertise with strong delivery ownership across solutioning, engineering execution, stakeholder management, and production rollout.

The ideal candidate will have hands-on experience building and scaling multi-agent systems, RAG pipelines, LLM-powered applications, and AI platform components in production environments, while also leading technical teams and ensuring reliable delivery against business goals.

Ideal Candidate Profile :

The ideal candidate is someone who can own both architecture and delivery. They should be comfortable defining the technical direction for complex AI systems, while also ensuring the solution gets built, deployed, governed, and adopted successfully in production.

Key Responsibilities :

- Define scalable reference architectures for Agentic AI and GenAI platforms, including multi-agent orchestration, tool usage, memory, retrieval, and workflow design

- Lead the end-to-end technical delivery of GenAI solutions from discovery and design through development, testing, deployment, and hypercare

- Architect and guide implementation of RAG and Agentic RAG pipelines, including ingestion, chunking, indexing, retrieval, grounding, caching, and citation patterns

- Design multi-agent systems using patterns such as planner-executor, coordinator-worker, and human-in-the-loop workflows

- Drive production-grade implementation of tool/function calling frameworks, with schema validation, access controls, error handling, and safe execution

- Own technical decision-making across platform design, APIs, integration patterns, cloud deployment, security, scalability, and reliability

- Establish evaluation and quality frameworks for LLM systems covering grounding, hallucination control, latency, cost, observability, and release readiness

- Partner with product, business, and engineering stakeholders to translate business requirements into practical AI solution architectures and delivery plans

- Lead architecture reviews, sprint-level technical direction, risk identification, and issue resolution across delivery teams

- Ensure production readiness through monitoring, logging, runbooks, performance tuning, and operational governance

- Mentor engineers and technical leads, and drive engineering best practices across modular design, testing, documentation, and deployment

- Contribute to client discussions, technical workshops, effort estimation, solution proposals, and implementation roadmaps where required

Must-Have Skills & Experience :

- 6 to 12 years of experience in backend engineering, platform engineering, AI engineering, or solution architecture, with strong technical leadership experience

- Proven experience delivering production-grade GenAI / Agentic AI solutions in enterprise settings

- Strong hands-on expertise in Python, including API development, modular architecture, async programming, testing, and performance optimization

- Deep understanding of RAG architectures, vector retrieval patterns, prompt orchestration, and grounding strategies

- Strong experience with multi-agent frameworks and orchestration patterns, such as

LangGraph, Semantic Kernel, MCP, A2A-aware systems, or similar

- Experience leading end-to-end delivery across solution design, engineering execution, deployment, and production support

- Strong understanding of LLM evaluation frameworks, observability, and quality controls for enterprise AI systems

- Experience with cloud-native architecture, containers, CI/CD, authentication, resilient APIs, and secure integration patterns

- Ability to lead cross-functional teams and work closely with stakeholders across product,

engineering, platform, and business functions

- Strong communication skills with the ability to drive technical discussions with both engineering and non-engineering stakeholders

Preferred Technical Exposure :

- Azure OpenAI, Azure AI services, AWS Bedrock, or equivalent enterprise AI platforms

- LangChain, LangGraph, Semantic Kernel, MCP, A2A, FastAPI

- Vector databases and retrieval stacks such as FAISS, Weaviate, Pinecone, ChromaDB, OpenSearch, or similar

- Docker, Kubernetes, API gateways, Redis/cache layers, CI/CD pipelines

- Observability and evaluation tools such as MLflow, Arize, Phoenix, OpenTelemetry, or

equivalent

- Enterprise integrations with platforms such as SAP, Salesforce, ServiceNow, or other

operational systems

- Experience with on-prem or hybrid deployments, especially for security-sensitive or regulated

environments

- Exposure to Responsible AI, governance, compliance, access control, auditability, and model risk management

Delivery & Leadership Expectations :

- Own delivery outcomes for AI workstreams, not just architecture design

- Balance hands-on technical depth with practical execution and team enablement

- Drive structured delivery governance including planning, prioritisation, risk tracking, and

release readiness

- Work effectively in fast-moving environments where solutions must move from PoC to

production with clarity and accountability

- Provide technical leadership across architecture, implementation, and stakeholder alignment

Good to Have :

- Experience building enterprise AI platforms serving multiple use cases or large user bases

- Prior experience in consulting-led, client-facing, or product engineering environments

- Familiarity with cost optimisation strategies across LLM, infra, and inference layers