Cloud Architect

If you need support in completing the application or if you require a different format of this document, please get in touch with at or call TCS London Office number with the subject line: “Application Support Request”.

Job Type: Permanent

Location: Luton, UK (Hybrid)

Number of hours: 40 hours per week – full time

Are you looking for an exciting opportunity in AWS Generative AI capabilities?

Are you passionate about Generative AI?

We have an exciting role for you
- AWS Gen AI Architect

Careers at TCS:
It means more

TCS is a purpose‑led transformation company, built on belief. We do not just help businesses to transform through technology. We support them in making a meaningful difference to the people and communities they serve - our clients include some of the biggest brands in the UK and worldwide. For you, it means more to make an impact that matters, through challenging projects which demand ambitious innovation and thought leadership.

• Build strong relationships with a diverse range of stakeholders.
• Gain access to endless learning opportunities.
• Work closely with the range of teams within the business to bring products to life.

As an AWS Generative AI Architect you will be responsible for defining the end‑to‑end architecture, reference designs, and governance for Generative AI solutions across voice and chat channels. This role partners with product owners, security, data, and engineering teams to translate business outcomes into scalable, secure, and cost‑optimised architectures on AWS, accelerating delivery of conversational AI products using Amazon Bedrock, agentic frameworks, and retrieval‑augmented generation (RAG) patterns.

• Own the target‑state architecture for GenAI products (voice and chat), including multi‑account strategy, landing zone alignment, network patterns, and environment segregation (dev/test/prod).
• Define reference architectures for Amazon Bedrock, model orchestration, RAG, tool/function calling, and agentic workflows (e.g., Lang Chain/Lang Graph/CrewAI/Strands‑style patterns) with clear guardrails.
• Design enterprise‑grade knowledge architectures: ingestion pipelines, chunking strategies, embedding/model choices, vector stores, metadata/ACL strategy, and evaluation loops to improve retrieval quality.
• Architect APIs and integration layers for GenAI agents (API Gateway/ALB, VPC integration, event‑driven patterns), including connectivity to external systems and MCP‑style tool servers where applicable.
• Establish security, privacy, and compliance‑by‑design: IAM least privilege, KMS encryption, secrets management, data classification, PII redaction, prompt/response filtering, and model governance.
• Drive non‑functional requirements: reliability, scalability, latency, observability, DR, and cost controls (Fin Ops) for GenAI workloads.
• Guide build teams through solution design, reviews, and implementation; produce architecture artefacts (HLD/LLD), patterns, and decision records; mentor developers and engineers.
• Define evaluation and monitoring strategy: offline test sets, automated regression, hallucination detection, safety metrics, guardrail effectiveness, and production telemetry.
• Support stakeholder engagement and client‑facing workshops to shape roadmaps, prioritise use cases, and align on success criteria

• Strong hands‑on architecting experience with AWS, including Well‑Architected Framework, multi‑account design, networking, and security patterns.
• Deep understanding of LLM concepts (prompting, tool use, retrieval, grounding, evaluation) and GenAI risk controls (hallucination, toxicity, PII leakage, prompt injection).
• RAG architecture expertise: data ingestion, embeddings, vector search, re‑ranking, response synthesis, and continuous improvement using feedback signals.
• API and integration design experience, including event‑driven architectures and secure connectivity to enterprise systems.
• Proficiency in one or more languages (Python/Node.js preferred) and infrastructure‑as‑code (CDK/Cloud Formation/Terraform) for repeatable deployments.
• Experience setting up observability for GenAI: tracing, logging, metrics, and…