About the Role

We are seeking an experienced AI Agentic Solutions Architect to design and lead enterprise-scale agentic AI platforms. This role is focused on architecting advanced multi-agent systems, LLMOps platforms, RAG solutions, and Responsible AI frameworks while establishing engineering standards for scalable, secure, and production-ready AI applications.

Key Responsibilities

- Define enterprise architecture standards for agentic AI, including agent design patterns, deployment topology, evaluation strategies, and Responsible AI governance.

- Design and implement advanced multi-agent systems with supervisor hierarchies, agent delegation, shared memory, agent-to-agent communication, and orchestration workflows.

- Architect scalable Retrieval-Augmented Generation (RAG) platforms using Azure AI Search, vector databases, GraphRAG, and Knowledge Graph technologies.

- Build and optimize LLMOps platforms using PromptFlow, LangSmith, model evaluation frameworks, AI observability, and cost optimization strategies.

- Design Responsible AI frameworks, including guardrails, content safety, bias detection, audit logging, and governance controls.

- Develop evaluation frameworks with offline benchmarks, online monitoring, A/B testing, and human feedback mechanisms.

- Collaborate with Data Engineering teams to design data pipelines, knowledge bases, and fine-tuning datasets for AI solutions.

- Drive architecture reviews, establish engineering best practices, and mentor development teams on enterprise AI standards.

- Ensure production resilience through model routing, fallback strategies, checkpointing, token optimization, and multi-provider LLM deployments.





Key Skills & Qualifications

- 10+ years of software engineering experience with strong expertise in Python and Java or .NET.

- Deep architectural expertise in LangChain, LangGraph, and enterprise AI application development.

- Hands-on experience with Semantic Kernel, CrewAI, AutoGen, and LlamaIndex.

- Strong knowledge of Azure AI Search, Vector Databases, GraphRAG, Neo4j, and Knowledge Graph architectures.

- Experience building enterprise RAG platforms and AI knowledge retrieval systems.

- Expertise in PromptFlow, LangSmith, AI observability, model evaluation, and LLMOps best practices.

- Strong understanding of Responsible AI principles, including fairness, bias detection, explainability, and governance.

- Experience with model routing, token budgeting, rate-limit handling, multi-provider LLM architectures, and production AI operations.

- Experience deploying scalable AI solutions on AWS or Azure (cloud certification preferred).

- Excellent technical leadership, architecture review, stakeholder management, and mentoring skills.

Preferred Skills

- Experience with Model Context Protocol (MCP) and AI tool ecosystem governance.

- Knowledge of prompt injection prevention, secure agent execution, and AI security best practices.

- Experience with fine-tuning techniques including LoRA, RLHF, and DPO.

- Familiarity with MLflow for experiment tracking and model lifecycle management.

- Experience using AI-assisted development tools such as Claude Code and Cursor.

- Robust understanding of Architecture Decision Records (ADRs) and enterprise design governance.

Apply by sending your CV to [email protected]

📌 Agentic Architect (Pune)
🏢 gts
📍 Pune