IN_ Manager_ Agentic AI/ GenAI Architect _AppTech_Advisory_ Kolkata (Immediate joiners)

PwC India; Kolkata District; On-site; INR 3,500,000 - 7,000,000; Full time

Job summary

PwC India in Kolkata seeks an experienced GenAI Architect/Lead to drive enterprise GenAI adoption and design scalable, production‑grade AI solutions. You will lead GenAI developers, collaborate with architects, product owners, and leadership to translate business goals into architectures and accelerators.

The role emphasizes advanced RAG, semantic search, and agentic AI workflows, with focus on secure, observable, and cost‑efficient systems across the SDLC.

Qualifications

• 9+ years of experience in GenAI/LLM ecosystems.
• Experience in enterprise GenAI architecture & governance.

Responsibilities

• Lead GenAI developers and backend engineers to deliver enterprise GenAI applications and accelerators.
• Translate business requirements into technical designs, work breakdowns, and implementation plans.
• Review architecture, code, prompt design, RAG pipeline design, data model, API design, and integration approaches.
• Ensure quality, performance, security, maintainability, observability, and production readiness.

Skills

GenAI Architecture

RAG & Semantic Search

Agentic AI

Backend API Design

MCP & A2A

Observability

Security & Governance

Education

BE/BTech/MCA/M.E./M.TECH/MBA/PGDM

Tools

LangGraph

LangChain

CrewAI

AutoGen

LlamaIndex

OpenTelemetry

Job description

Job Description & Summary: A career within Technology Consulting services will provide you with the opportunity to bring our clients a competitive advantage through defining their technology objectives, assessing solution options, and devising architectural solutions that help them achieve both strategic goals and meet operational requirements. We help build software and design data platforms, manage large volumes of client data, develop compliance procedures for data management, and continually research new technologies to drive innovation and sustainable change.

• We are looking for a highly experienced, hands‑on GenAI Architect/Lead to drive enterprise‑wide adoption of Generative AI and building Agentic AI solutions. This role combines deep technical expertise, solution architecture to enable GenAI‑led transformation across the SDLC and business workflows.
• You will work closely with engineering teams, architects, product owners, and leadership to design and implement scalable, production‑grade GenAI systems, while also acting as a thought leader and change agent for GenAI adoption.

Job Position Title: IN_ Manager_ Agentic AI/ GenAI Architect _AppTech_Advisory_ Kolkata (Immediate joiners)

Responsibilities

Technical Leadership & Delivery

• Lead a team of GenAI developers and backend engineers to deliver enterprise GenAI applications and accelerators.
• Translate business requirements into technical designs, work breakdown, implementation plans, and engineering tasks.
• Review architecture, code, prompt design, RAG pipeline design, data model, API design, and integration approaches.
• Ensure quality, performance, security, maintainability, observability, cost efficiency, and production readiness.

Advanced RAG, Semantic Search & Knowledge Architecture

• Design and optimize RAG pipelines including ingestion, chunking, metadata extraction, embeddings, vector indexing, hybrid retrieval, re‑ranking, citation generation, and answer synthesis.
• Implement semantic search across structured, semi‑structured, and unstructured knowledge sources.
• Integrate with enterprise knowledge repositories such as SharePoint, Confluence, S3, Google Drive, databases, ITSM tools, and document management systems.
• Define knowledge freshness, access‑controlled retrieval, lineage, deduplication, feedback loops, and retrieval quality improvement mechanisms.

Agentic AI & MCP-based Tool Integration

• Design and implement agentic workflows using LangGraph, LangChain, CrewAI, AutoGen, LlamaIndex, or equivalent.
• Implement tool calling, memory, workflow state, human‑in‑the‑loop approval, API actions, and safe execution boundaries.
• Build or guide MCP server implementations for secure agent‑to‑tool and LLM‑to‑enterprise‑system integration.
• Evaluate A2A communication patterns for multi‑agent collaboration, delegation, and hand‑offs where relevant.

Backend, API, Data & Event-Driven Engineering

• Build scalable services using Python, FastAPI, Node.js, Java, or similar technologies.
• Design REST APIs and microservices for LLM orchestration, semantic search, ingestion, agent execution, feedback, and evaluation.
• Use SQL and NoSQL databases for application metadata, session history, audit logs, feedback, configurations, and workflow state.
• Design Redis caching patterns for session state, memory, rate limiting, token optimization, retrieval caching, distributed locks, and workflow continuity.
• Design asynchronous workflows using Kafka, RabbitMQ, Azure Service Bus, AWS SQS/SNS, Google Pub/Sub, or equivalent, including retry, DLQ, idempotency, ordering, and schema management.

Evaluation, Observability, Security & Governance

• Implement LLM tracing, prompt/version tracking, token usage monitoring, latency tracking, cost monitoring, and feedback analytics.
• Define evaluation datasets and metrics for faithfulness, groundedness, answer relevance, context relevance, hallucination rate, toxicity, latency, and cost.
• Use LangSmith, Langfuse, RAGAS, DeepEval, TruLens, Promptfoo, OpenTelemetry, Grafana, Prometheus, ELK, Datadog, or equivalent.
• Implement guardrails against prompt injection, jailbreaks, data leakage, unauthorized tool execution, toxic responses, and privacy violations.
• Support AI‑assisted SDLC adoption using GitHub Copilot, Codex, CursorAI, Claude Code, Cline, or similar tools.

Mandatory skill sets

• Enterprise GenAI Architecture - Reference architecture, platform strategy, reusable accelerators, NFRs, governance
• RAG & Semantic Search - Hybrid search, BM25, vector DBs, embeddings, re‑ranking, citations, grounding
• Agentic AI - LangGraph, LangChain, CrewAI, AutoGen, planning, memory, human-in-the-loop
• MCP & A2A - MCP servers/gateways, tool ecosystem, secure execution, A2A multi‑agent patterns
• Backend API - Python, FastAPI, Node.js, Java, REST, microservices, OpenAPI, API gateways
• Observability - LangSmith, Langfuse, RAGAS, DeepEval, Promptfoo, OpenTelemetry, Grafana, Prometheus, ELK, Datadog, or equivalent.
• Data Architecture - SQL, NoSQL, vector DB, object storage, analytics stores, metadata, lineage, audit
• Caching - Redis, session continuity, memory, rate limiting, distributed locks, retrieval caching
• Messaging - Kafka, event‑driven design, RabbitMQ, DLQ, retry, idempotency, event schemas, async workflows
• Cloud & Model Strategy - Azure OpenAI, AWS Bedrock, GCP Vertex AI, OpenAI, Claude, Gemini, Hugging Face, SLMs
• LLMOps / MLOps / DevOps - Prompt/model versioning, evaluation gates, CI/CD, Docker, Kubernetes, Helm Chart, Terraform
• Security & Responsible AI – Guardrails, prompt injection, LLM Shield, PII, privacy, compliance, audit, model risk management

Preferred Skills

Relevant Certifications preferred.

Years of experience required

9+ years (with exposure GenAI/LLM ecosystems)

Education qualification

B.E. / B.Tech / MCA/ M.E/ M.TECH/ MBA/ PGDM. All qualifications should be in regular full-time mode with no extension of course duration due to backlogs.