Experience: 12+ Years

Role Summary

- Architect agentic solutions end to end: task decomposition, tool/function design, memory and state models, orchestration topology (supervisor, hierarchical, sequential, parallel), and human-in-the-loop checkpoints.
- - Design and tune production RAG pipelines — chunking, hybrid retrieval, reranking, query rewriting, metadata filtering, grounding and citation — and own the retrieval quality metrics, not just the pipeline diagram.

- - Build the evaluation layer alongside the system: golden datasets, trace-level assertions, LLM-as-judge rubrics, regression suites that gate deployment.

- - Select and justify the AWS service composition for each workload, with an explicit view on cost, latency, data residency, and failure modes.

- - Define guardrails and the security posture for agents that take real actions: least-privilege tool permissions, prompt injection defenses, PII handling, audit trails.

- - Set engineering standards for the practice — reference architectures, reusable agent and tool patterns, observability conventions — and mentor engineers into them.

- - Partner with client stakeholders on solution shaping, technical discovery, effort estimation, and proof-of-value scoping.

Why This Role Matters Agentic AI systems fail in production for predictable reasons: unmanaged context windows, brittle orchestration, unscoped tool permissions, and no observability into why an agent did what it did. This role exists to prevent that — designing agent architectures on AWS (Bedrock, AgentCore, SageMaker) that are secure by default, cost-bounded, evaluable, and built to scale past the POC stage

What You’ll Do

We are seeking a strong AWS AI architect with hands-on expertise with At least two agentic or RAG systems taken to production on AWS, with evidence of ownership through the operate phase — not pilots that stopped at demo.

Must-Have Skills

2-3 year experience in Agentic system design Planning and execution loops, ReAct and plan-execute patterns, tool/function calling design, short- and long-term memory, state persistence and recovery, multi-agent orchestration and handoff design, MCP and A2A for tool and agent interoperability. Practical judgment on when an agent is the wrong answer and a deterministic workflow is the right one.

2-3 year experience in Agent frameworks Deep hands-on experience with at least two of: Strands Agents SDK, LangGraph, CrewAI, AutoGen, LlamaIndex. Comfortable dropping to a custom orchestration loop where a framework gets in the way.





3 year experience in RAG engineering Production experience with document processing and chunking strategy, embedding model selection, vector and hybrid (BM25 + dense) retrieval, reranking, query decomposition, GraphRAG and agentic RAG patterns, context-window budgeting, and grounding/citation enforcement. Able to diagnose whether a bad answer came from retrieval, ranking, or generation.

AWS AI stack – 3 years of experience –

Amazon Bedrock — Converse API, model selection and routing, Knowledge Bases, Guardrails, Flows, prompt caching, batch vs. real-time inference and Amazon Bedrock AgentCore — Runtime, Memory, Gateway, Identity, Observability, Code Interpreter, Browser

Amazon SageMaker AI for custom model hosting, training, and endpoint operations and Vector and search: Amazon OpenSearch Serverless, S3 Vectors, Aurora PostgreSQL with pgvector, Amazon Kendra.

5 years of experience in AWS core services Lambda, Step Functions, ECS/EKS/Fargate, API Gateway, EventBridge, SQS, DynamoDB, S3, CloudWatch, IAM, KMS, Secrets Manager, VPC and PrivateLink. Able to design a VPC-isolated, private-endpoint deployment for a regulated client without help.

7+ years of experience in Python engineering Production-grade Python — async, typing, Pydantic, FastAPI, structured testing. Clean, reviewable code; not notebook-only.

2+ years of experience Evaluation and LLMOps Offline and online evaluation design, RAGAS or equivalent retrieval metrics, trace-based observability (OpenTelemetry GenAI conventions, CloudWatch, Langfuse/LangSmith or similar), prompt and model versioning, token and cost governance, drift and regression detection.

2+ years of experience AI security and responsible AI Prompt injection and tool-abuse threat modeling, scoped tool permissions and action approval design, data classification and PII handling, content filtering, auditability. Working familiarity with an AI governance framework such as NIST AI RMF.

Good to Have

Model optimization — fine-tuning and LoRA/QLoRA, distillation into smaller or open-weight models, SLM deployment, structured decoding, latency/cost optimization under SLA.

Multimodal and voice — Amazon Nova models, Transcribe, Polly,



real-time voice agent architectures and Infrastructure as code and CI/CD — AWS CDK or Terraform, GitHub Actions or CodePipeline, containerization, environment promotion strategy.

Data engineering foundations — AWS Glue, Kinesis, Kafka/Confluent, Lake Formation, Iceberg; designing the ingestion layer that feeds retrieval and Enterprise integration — SharePoint, ServiceNow, Salesforce, SAP, Confluence/Jira connectors and their authentication realities.

Regulated-industry delivery — HIPAA, GxP, SOC 2, or FedRAMP contexts; EU AI Act awareness and Frontend for AI — React or Streamlit for rapid proofs of value, streaming UX (SSE/WebSocket), interrupt and approval interfaces.

What Success Looks Like (6–12 Months)

Agentic AI systems move from prototype to production with defined SLAs, scoped permissions, and continuous evaluation — not fragile demos that break under real usage. Your architectural patterns become the org’s reusable default, cutting time-to-production for every team that builds after you.

Why Join WinWire: Your Path to Professional Excellence in the Age of AI

As an Employer of Choice, WinWire offers an exceptional workplace culture, industry recognition, and an unwavering commitment to employee growth. Here is why top talent chooses us:

- AI-First. Globally Recognized: Honored at the World Economic Forum in Davos for our pioneering "Agentic AI @ Scale" work, cementing our position as a forward-thinking, AI-first services firm shaping the future of enterprise technology.
- Microsoft Gold Standard: A 6x Microsoft Global Partner of the Year Winner/Finalist — reflecting our consistent delivery of industry-leading solutions and our deep, trusted partnership with Microsoft.
- Joining the NTT DATA Family: WinWire (Part of NTT DATA), a $30 billion global leader in AI, digital business, and technology services. This means greater career stability, broader client exposure, and access to a vast landscape of opportunities across a truly global organization.
- Award-Winning Culture: Certified as a Best Place to Work® four times, our workplace culture is not just a talking point — it is a proven, recognized commitment to creating an environment where people genuinely thrive.
- People-First Environment: With a robust 4.0 Glassdoor rating, our employees speak for themselves. We prioritize wellbeing, inclusivity, and a culture of respect at every level of the organization.
- Invest in Your Growth: From continuous learning programs to structured career development pathways, we equip our team with the skills, tools, and opportunities needed to grow and lead in the age of AI.

📌 Technical Architect – AWS AI Architect (Bengaluru)
🏢 WinWire
📍 Bengaluru