Description

Lead end-to-end enterprise GenAI and ML architecture from discovery through production, ensuring scalability, security, and measurable business value.

This role is on-site.

Responsibilities

• Design solution blueprints with HLD/LLD and Lucid diagrams, covering integrations, NFRs, data flows, and deployment operations.
• Architect advanced RAG systems including ingestion pipelines, hybrid retrieval, reranking, citation, and vector data models for low-latency enterprise knowledge.
• Define Prompt Engineering standards: system prompts, few-shot patterns, JSON schemas, guardrails, versioning, and automated regression testing.
• Lead AI Agent design with tool/function calling, planning loops, memory strategies, and human-in-the-loop approvals.
• Drive MLOps/LLMOps practices: CI/CD, model versioning, drift monitoring, cost controls, canary releases, and rollback strategies.

Required Skills

• 10+ years of experience in enterprise architecture, with specific focus on GenAI/ML systems.
• Experience with Cloud-native GenAI solutions, specifically Google Vertex AI, Gemini, BigQuery, and Cloud Storage.
• Proficiency with Agentic AI frameworks: LangChain, LangGraph, and LangSmith.
• Strong background in RAG architectures: chunking strategies, embeddings, indexing, and retrieval optimization.
• Expertise in LLMops/MLOps: automated evaluations, monitoring, and production readiness.
• Experience with On-Premises and Cloud environments.
• Ability to design Agentic Workflows with fail safes, escalation paths, and auditability.
• Knowledge of MCP (Model Context Protocol) integrations and A2A collaboration patterns.

Preferred Skills

• Experience with payments-grade security, privacy, and compliance (IAM, encryption, PII controls).
• Ability to mentor teams and evangelize AI engineering culture through reusable reference architectures.

Key Skills

Education

Any Graduate