Senior GenAI Solutions Architect – Enterprise RAG & LLM

Tata Consultancy Services Limited; Addison (TX); Hybrid; USD 100,000 - 140,000; Full time

Job summary

Tata Consultancy Services Limited is seeking a Senior Generative AI Solutions Architect to lead the design and scaling of an enterprise-grade Document Intelligence platform within the DCRS Inbound Correspondence team.

The role focuses on defining architecture for LLM-powered solutions enabling document classification, data extraction, and retrieval-augmented generation across large document ecosystems, with emphasis on performance and regulatory compliance.

Qualifications

• 8+ years of experience in software or solution architecture.
• 3+ years of experience in AI/ML or Generative AI.
• Strong hands-on expertise with LLMs and GenAI frameworks (OpenAI, Hugging Face, LLaMA, Mistral).
• Embeddings and vector search technologies (Elasticsearch, Pinecone, FAISS).
• Advanced proficiency in Python, including FastAPI, LangChain / LlamaIndex.
• Proven experience designing and implementing RAG-based solutions at enterprise scale.
• Experience with GPU-based model serving and optimization (vLLM, Triton).
• Cloud-native architectures and microservices; MLOps practices (CI/CD, monitoring, versioning).
• Strong understanding of risk, compliance, and governance in regulated environments.
• Excellent communication skills for executive stakeholders.

Responsibilities

• Architect and deliver scalable GenAI solutions for document classification, data extraction, and retrieval-augmented generation (RAG).
• Design end-to-end RAG architectures with embeddings, chunking, and vector DB selection.
• Lead deployment strategies for LLM inference at scale with GPU-based environments.
• Establish model governance: explainability, audit trails, and benchmarking pipelines.
• Define reference architectures, standards, and best practices for GenAI adoption enterprise-wide.
• Produce architecture artifacts: diagrams, design docs, roadmaps, and executive materials.
• Collaborate with Engineering, Product, Risk, and Compliance to ensure safe, scalable solutions.

Skills

GenAI architecture

Data science

Python

Communication with executives

Education

Master's degree in Computer Science or related field

Bachelor's degree in Computer Science

Tools

OpenAI

Hugging Face

LLaMA

Mistral

Elasticsearch

Pinecone

FAISS

FastAPI

LangChain

LlamaIndex

vLLM

Triton

Job description

Tata Consultancy Services Limited is seeking a Senior Generative AI Solutions Architect to lead the design and scaling of an enterprise-grade Document Intelligence platform within the DCRS Inbound Correspondence team.

The role focuses on defining architecture for LLM-powered solutions enabling document classification, data extraction, and retrieval-augmented generation across large document ecosystems, with emphasis on performance and regulatory compliance.