Role & responsibilities

Key Responsibilities

- Architect and deploy an enterprise AI Gateway using proven multi-provider LLM

gateway patterns (e.g., LiteLLM) for routing, access control, cost management, and

observability.

- Define reference architectures and standards for integrating multiple LLM providers

(Azure OpenAI, AWS Bedrock, OpenAI, Anthropic).

- Support and migrate existing AI POCs and AI platform-led products into production

through standardized AI Gateway patterns.

- Design and deliver an Enterprise Knowledge Search MVP using production-grade

Retrieval-Augmented Generation (RAG) architectures.

- Lead additional enterprise Knowledge Search implementations, including consolidation

and modernization of FIN and OR&R; search capabilities.

- Establish AI evaluation and validation frameworks, including rubric-based quality

scoring, automated RAG testing, and regression evaluation pipelines.

- Define AI development standards, reusable components, and approved tooling in

partnership with the Engineering Excellence team.

- Establish AI testing guidelines covering accuracy, grounding, safety, performance, cost,

and operational resilience.

- Own and govern the enterprise Writer.AI platform, including architecture, security

configuration, integrations, access models, usage standards, and roadmap alignment.

- Serve as the architectural authority for Writer.AI adoption across business units,

ensuring consistent usage patterns, compliance, and measurable value realization.

- Embed responsible AI principles including security, privacy, auditability, and

compliance into all AI architectures and platforms.

Required Qualifications

- 12+ years of experience in software or platform architecture, with 5+ years in AI/ML or

Generative AI systems.

- Proven experience architecting enterprise-scale LLM platforms, AI gateways, and GenAI

products.





- Hands-on experience owning or governing enterprise GenAI platforms such as Writer.AI

or equivalent.

- Strong expertise in Retrieval-Augmented Generation (RAG) and enterprise knowledge

search architectures.

- Experience defining AI evaluation, testing, and validation frameworks for LLM-based

systems.

- Experience designing cloud-native solutions on Azure, AWS, or GCP.
- Solid ability to influence cross-functional stakeholders across engineering, security,

compliance, and governance teams.

- Bachelors or Master’s degree in Computer Science, Engineering, or related field.

Preferred Experience

- Experience with enterprise LLM gateways such as LiteLLM or equivalent proxy-based

architectures.

- Experience with AI orchestration frameworks such as LangChain, LlamaIndex, or

Semantic Kernel.

- Experience implementing AI observability, monitoring, and LLMOps solutions.
- Experience working in regulated or large-scale enterprise environments.

Tools & Frameworks (Industry-Aligned)

LLM Gateway & Platforms: LiteLLM, Azure AI Studio, AWS Bedrock.

Enterprise GenAI Platforms: Writer.AI (enterprise content generation, governance, and

controls).

RAG & Knowledge Search: LangChain, LlamaIndex, Azure AI Search, OpenSearch, Pinecone,

Weaviate, pgvector.

AI Validation & Testing: RAGAS, DeepEval, Promptfoo, rubric-based evaluation frameworks.

Observability & LLMOps: LangSmith, Arize Phoenix, Weights & Biases.

Cloud & Platform: Azure, AWS, Docker, Kubernetes, Terraform.

Security & Governance: IAM, Secrets Management, audit logging, Responsible AI

frameworks (e.g., NIST AI RMF).

Why This Role Matters

This role provides the architectural foundation for scaling Generative AI safely and

effectively across the enterprise. By standardizing LLM access, enforcing rigorous

validation, and owning platforms such as Writer.AI, the Enterprise AI Architect ensures

consistent quality, reduced risk, and accelerated business value from AI investments

📌 Enterprise Architect-14+ (Hyderabad)
🏢 Cloudxtreme
📍 Hyderabad