ob Description – Consultant (AI Center of Excellence – Generative AI)

Experience: 3–7 Years

Location: Mumbai

Role Summary

We are looking for a Consultant/ Sr Consultant/ manager with 3–7 years of experience in AI/ML and Generative AI to design, develop, and implement enterprise-grade GenAI solutions. The ideal candidate should have hands-on experience with LLMs, Retrieval-Augmented Generation (RAG), Agentic AI, Vector Databases, and enterprise AI governance. Experience in delivering scalable AI solutions in Banking/Financial Services is preferred.

Key Responsibilities

· Design and implement end-to-end Generative AI and RAG-based applications.

· Build scalable document retrieval solutions using embeddings, vector databases, and semantic search.

· Develop Agentic AI solutions with multi-agent orchestration and tool/function calling.

· Optimize GenAI applications for accuracy, latency, scalability, and cost.

· Implement AI guardrails, security, and governance for enterprise deployments.

· Collaborate with business and technology teams to deliver production-ready AI solutions.

Required Skills

· Solid experience with Python and enterprise AI application development.

· Hands-on experience with LLMs (OpenAI, Azure OpenAI, Claude, Gemini, Llama, etc.).

· Expertise in Embeddings, Indexing, Vector Databases, Retrieval, and RAG architecture.

· Experience with LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen,



or similar frameworks.

· Strong understanding of Cross Encoders, reranking, prompt engineering, and hallucination mitigation.

· Experience designing Agentic AI workflows, agent routing, orchestration, memory, and tool integration.

· Knowledge of LLM selection, model evaluation, and optimization techniques.

· Experience implementing AI guardrails, prompt injection prevention, PII masking, content moderation, and Responsible AI practices.

· Familiarity with cloud platforms (Azure, AWS, or GCP) and REST APIs.

Interview Focus Areas

Candidates should be able to demonstrate:

· End-to-end project walkthrough with architecture and implementation details.

· In-depth understanding of Embeddings, Indexing, Retrieval, and scalable RAG pipelines.

· Cross Encoder and reranking concepts with practical implementation.

· Hallucination handling strategies in enterprise applications.

· End-to-end RAG pipeline design and optimization.

· Agentic AI concepts, including agent configuration, routing, orchestration, and tool calling.

· LLM selection approach based on business, cost, performance, and security considerations.

· Performance optimization techniques for GenAI applications.

· Enterprise AI governance and guardrails implemented in production.

Preferred Domain: Banking / Financial Services (BFSI) experience is an added advantage.

📌 Consultant (AI Center of Excellence – Generative AI) - Deloitte (Mumbai)
🏢 Trigent Software
📍 Mumbai