Enterprise AI Architect(Eval, DeepEval, Ragas)_Immediate

Kezan Consulting; Gurugram District, Bengaluru; On-site; INR 4,000,000 - 8,000,000; Full time

Job summary

Kezan Consulting is seeking a senior AI Architect to design and deploy enterprise-scale Generative AI and LLM-based solutions in a Gurgaon-based setting. You will lead projects spanning RAG-based apps, vector databases, and AI governance, collaborating with cross-functional teams to deliver scalable AI systems.

You will evaluate and optimize prompts, pipelines, and architectures, with deep experience in cloud-native distributed systems, MLOps, and modern AI stacks.

Qualifications

• Bachelor's/Master's in Computer Science, AI, Data Science, or related field.
• 10+ years of software engineering experience with 4-5+ years in AI/Generative AI architecture.
• Proven experience designing enterprise AI platforms and LLM-based applications.
• Strong expertise in AI evaluation, cloud-native architecture, and scalable distributed systems.

Responsibilities

• Design and implement enterprise-scale Generative AI and LLM-based solutions.
• Build RAG-based applications using vector databases and AI orchestration frameworks.
• Develop AI evaluation pipelines using DeepEval and Ragas.
• Optimize LLM performance through prompt engineering, evaluation, and monitoring.
• Define AI architecture standards, governance, and best practices.
• Collaborate with engineering teams to deliver scalable, production-ready AI systems.

Skills

OpenAI

Claude

Gemini

Llama

Mistral

RAG

Agentic AI

Prompt Engineering

Multi-Agent Systems

DeepEval

Ragas

LangChain

LlamaIndex

Hugging Face

Vector Databases

Pinecone

Weaviate

Milvus

ChromaDB

FAISS

Python

FastAPI

REST APIs

SQL

AWS

Azure

GCP

Docker

Kubernetes

MLflow

Education

Bachelor's/Master's in Computer Science, AI, Data Science, or related field

Tools

OpenAI

Claude

Gemini

Llama

Mistral

Job description

Key Responsibilities

• Design and implement enterprise-scale Generative AI and LLM-based solutions.
• Build RAG-based applications using vector databases and AI orchestration frameworks.
• Develop AI evaluation pipelines using DeepEval and Ragas.
• Optimize LLM performance through prompt engineering, evaluation, and monitoring.
• Define AI architecture standards, governance, and best practices.
• Collaborate with engineering teams to deliver scalable, production-ready AI systems.

Required Skills

• LLMs: OpenAI, Claude, Gemini, Llama, Mistral
• RAG, Agentic AI, Prompt Engineering, Multi-Agent Systems
• DeepEval & Ragas (Mandatory)
• LangChain, LlamaIndex, Hugging Face
• Vector Databases: Pinecone, Weaviate, Milvus, ChromaDB, FAISS
• Python, FastAPI, REST APIs, SQL
• AWS/Azure/GCP, Docker, Kubernetes, MLflow

Qualifications

• Bachelor's/Master's in Computer Science, AI, Data Science, or related field.
• 10+ years of software engineering experience with 4-5+ years in AI/Generative AI architecture.
• Proven experience designing enterprise AI platforms and LLM-based applications.
• Strong expertise in AI evaluation, cloud-native architecture, and scalable distributed systems.

Preferred: Knowledge of LLMOps, Knowledge Graphs, GraphRAG, AI Governance, AI Safety, and Enterprise Integrations.