AWS , AIML , Gen AI/ Agentic AI Architect

Tata Consultancy Services; Hyderabad, Pune District, Bengaluru; On-site; INR 900,000 - 1,800,000; Full time

Job summary

Tata Consultancy Services is seeking a GenAI Architect to design and deliver Generative AI and agentic architectures on AWS, leveraging Bedrock and SageMaker. The role focuses on prompt engineering, guardrails, tool calling, memory, evaluation, and multiagent patterns.

You will define model selection strategies, establish GenAI reference architectures for enterprise adoption, and build RAG systems with vector stores.

Qualifications

• Experience designing GenAI and agentic architectures.
• Ability to balance latency, cost and quality for models.
• Experience implementing RAG and knowledge systems.
• Strong MLOps capabilities including monitoring and drift detection.
• Knowledge of security, governance and Responsible AI controls.

Responsibilities

• Design Generative AI architectures on AWS with Bedrock and SageMaker.
• Define model selection strategies and reference architectures.
• Build RAG systems using vector stores and embeddings.
• Implement MLOps pipelines, monitoring and approvals.
• Define end-to-end security, IAM, KMS and governance controls.
• Lead architecture reviews and mentor engineers.

Skills

GenAI architecture

Cloud architecture

Prompt engineering

RAG & embeddings

MLOps

Tools

AWS Core

Bedrock / SageMaker

Vector stores

Guardrails

Job description

Role & responsibilities

GenAI Architecture

• Design and deliver Generative AI and agentic architectures on AWS using Amazon Bedrock and SageMaker AI, including prompt engineering, guardrails, tool/function calling, memory, evaluation, and multiagent patterns.
• Define model selection strategies (foundation vs finetuned vs hosted OSS models) with latency, cost, and quality tradeoffs.
• Establish GenAI reference architectures for enterprise adoption.

RAG & Knowledge Systems

• Build RetrievalAugmented Generation (RAG) systems using:
• Vector stores: Amazon OpenSearch (vector engine), Aurora PostgreSQL (pgvector), DynamoDB (vector search), Pinecone

MLOps / LLMOps

• Monitoring, drift detection, approval, rollback
• Implement feature engineering and feature management using SageMaker AI (integrated feature store capabilities).

Security, Governance & Responsible AI

• Define endtoend security architecture for GenAI:
• IAM, KMS, secrets management
• Enforce Responsible AI controls: guardrails, moderation, auditability, traceability.

Stakeholder Engagement & Enablement

• Lead architecture reviews and design forums.
• Mentor engineers and architects across teams.
• Support solutioning, estimation, PoCs, and RFP responses for GenAI initiatives.

Preferred candidate profile

Core Skills & Qualifications (Refined)

AWS Core

Musthave

• VPC, IAM, KMS, CloudWatch, CloudTrail
• S3, DynamoDB, RDS/Aurora
• EKS / ECS / Lambda
• API Gateway, EventBridge, SQS, SNS

GenAI & AI/ML

Musthave

• Amazon Bedrock (models, guardrails, evaluation)
• SageMaker AI (training, hosting, pipelines)
• Prompt engineering, RAG, embeddings, evaluation

Cost/latency optimization strategies