Job Description Summary:

Lead the programs architecture and secure engineering guardrailsdefining reference patterns, reusable components, and SDLC quality standards to deliver productiongrade GenAI solutions at enterprise scale.

Responsibilities include

leading design reviews, shaping solution blueprints, writing proofofconcept code where needed, and ensuring security, reliability, and responsible AI practices are embedded endtoend.

Required Qualifications

HandsOn Technical Expertise (Recent and Demonstrable)

- Backend / AI: Python (FastAPI preferred), Node.js/TypeScript; LangChain, LangGraph; Azure OpenAI / OpenAI patterns for production.
- Frontend: React (TypeScript) familiarity to guide fullstack patterns.
- Data: PostgreSQL / Azure SQL / SQL Server; vector/RAG concepts and data access patterns.
- DevSecOps: Azure DevOps or GitHub Actions, Docker, IaC (Terraform/Bicep), secrets management, and security scanning integration.

- Quality Engineering: automated testing strategies (Playwright or equivalent), plus experience defining quality gates.

Architectural Leadership

- Proven experience designing complex, scalable, secure systems and guiding multiple engineering teams through design decisions and tradeoffs.
- Strong ability to drive engineering standards and governance through influence, reviews, and enablement (not command-and-control).

Key Responsibilities

1) Architecture & Technical Direction

- Define and own reference architectures for LLMpowered applications, agentic workflows, and platform-integrated solutions (RAG, tools, orchestration, APIs).
- Lead architecture decisions for scalability, cost, latency, observability, and resiliency across the program.
- Create and maintain standard patterns: agent orchestration, prompt/response flows, data access, caching,



and secure tool execution.

2) Secure Engineering & Guardrails (SecurebyDesign)

- Establish secure coding practices and enforce security guardrails throughout the SDLC (threat modeling, secrets handling, least privilege, secure APIs, secure prompt/tooling patterns).
- Partner with security stakeholders to ensure solutions align to enterprise security and privacy architecture principles and controls.
- Define program-wide standards for identity, access, and auditing across users, agents, and services (e.g., Entra ID patterns, policy enforcement, traceability).

3) AINative SDLC Enablement & Quality

- Set up and improve CI/CD pipelines and engineering playbooks (Azure DevOps/GitHub Actions) for repeatable delivery and compliance-ready releases.
- Drive test strategy for AI solutions: automated testing (e.g., Playwright), integration tests, and AI-specific validation (output quality, safety checks, regression/evaluation).

- Define engineering KPIs (lead time, deployment frequency, defects, reliability, security findings closure) and raise delivery maturity through coaching and reviews.

4) Reusable Components & HandsOn Prototyping

- Build proof-of-concepts, reference implementations, and reusable components that teams can adopt (starter kits, templates, scaffolds, shared libraries).
- Create golden paths” for common use cases: agent pattern templates, RAG pipelines, evaluation harnesses, telemetry hooks, and secure deployment blueprints.

5) Mentorship & Governance

- Lead design reviews and architecture workshops; ensure consistent application of standards without slowing delivery.
- Mentor engineers on modern AI development practices and effective use of AI coding assistants (e.g., GitHub Copilot / Cursor) while maintaining code quality and security standards.

📌 Fullstack Developer (Hyderabad)
🏢 Tata Consultancy Services
📍 Hyderabad