GenAI Architect

PwC; Hyderabad, Gurugram District, Bengaluru; Hybrid; INR 1,400,000 - 2,100,000; Full time

Job summary

PwC Hyderabad is seeking an experienced AI specialist to lead cutting-edge generative AI initiatives, scaling prototypes into enterprise-grade solutions across regions. You will optimize throughput, latency, and cost while ensuring secure, compliant deployments.

You will implement interoperability protocols such as MCP and A2A, work with LangChain and other frameworks, and apply Graph/Vectorless Hybrid RAG architectures within Kubernetes-based, cloud-native environments.

Qualifications

• Experience in developing and scaling Generative AI projects from prototypes to enterprise production.
• Experience implementing AI interoperability protocols at scale for seamless system integration.
• Hands-on with enterprise cloud AI platforms to build and deploy production-grade agentic AI solutions.

Responsibilities

• Develop and scale Generative AI projects from prototypes to enterprise production.
• Manage throughput, latency, cost, and multi-region deployments.
• Implement AI interoperability protocols at scale for seamless system integration.
• Build production-grade agentic AI solutions on cloud platforms.
• Apply advanced RAG architectures and AI/ML fundamentals in practice.
• Design defense-in-depth safeguards around LLMs and tool usage.
• Leverage containerization and cloud-native orchestration for scalable workloads.
• Pursue relevant AI or solution architecture certifications.

Skills

Generative AI project development

MCP & A2A interoperability

Python development

LLM security & safeguards

Agentic AI frameworks

RAG architectures

Cloud platforms (Azure Foundry, Bedrod

Kubernetes & Docker

AI/solution architecture certs

Tools

LangChain

LangGraph

CrewAI

AutoGen

Job description

Role & responsibilities

- Over 3 years of experience in developing and scaling Generative AI projects from prototypes to enterprise production, managing throughput, latency, cost, and multi-region deployments.

- Proven expertise implementing AI interoperability protocols like MCP (Model Context Protocol) and A2A (Agent-to Agent) at scale for seamless system integration.

- Skilled in using enterprise cloud AI platforms such as Azure AI Foundry, Amazon Bedrock, and Google Vertex AI to build and deploy production‑grade agentic AI solutions.

- Advanced Python programming skills and hands‑on experience with agentic AI frameworks including LangChain, LangGraph, CrewAI, and AutoGen for building robust generative AI applications.

- Deep understanding of advanced Retrieval Augmented Generation (RAG) architectures (Graph RAG, Vectorless RAG, Hybrid RAG) and traditional AI/ML fundamentals like model building, fine‑tuning, and evaluation.

- Strong knowledge of LLM security risksprompt injection, jailbreaking, data exfiltration, tool misuse—and experience designing defense‑in‑depth safeguards within agentic system architectures.

- Expertise in containerization and cloud‑native orchestration (Kubernetes, Docker, serverless) and event‑driven architectures for scalable deployment of agentic AI workloads; holds relevant AI or solution architecture certifications.