Principal Architect, AI Data Engineer

Jobtailor; Gurugram District; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Jobtailor in Gurugram, Haryana, India seeks a senior GenAI Architect to lead enterprise-grade GenAI architectures and RAG pipelines, driving scalable, reliable, and cost-optimized AI platforms. You will mentor teams and define reusable frameworks for organization-wide LLM applications.

The role requires 15+ years in data engineering/science/AI with hands-on GenAI experience and strong Python/PySpark and cloud expertise.

Qualifications

• 15+ years of total experience in Data Engineering / Data Science / AI
• 3+ years hands-on experience in LLM / GenAI solutions at scale
• Proven experience in architecture, solution design, and enterprise delivery
• Strong hands-on experience with LLMs (Claude, OpenAI, etc.)
• Experience with LangChain, LangGraph, or similar frameworks
• Strong Python/PySpark engineering expertise with proven API integration experience
• Deep data analysis experience and handling large volume of data
• Prior experience in Data Engineering (ETL/ELT, pipelines, orchestration)
• Good exposure to Cloud platforms (Azure/AWS/GCP)

Responsibilities

• Lead the design of enterprise-grade GenAI and agentic architectures (single-agent, multi-agent, tool-driven systems).
• Define reference architectures, reusable frameworks, and best practices for LLM applications across the organization.
• Architect and oversee end-to-end RAG pipelines: Data ingestion → chunking → embeddings → vector search → orchestration → response synthesis.
• Drive scalability, reliability, cost optimization, and performance across GenAI platforms.
• Provide technical leadership in prompt engineering, prompt orchestration, and agent workflows.
• Mentor and guide architects, engineers, and data scientists.

Skills

LLM Solutions

Data Engineering

Python/PySpark

Cloud Platforms

LangChain/LangGraph

API Integration

Data Analysis

ETL/ELT Pipelines

Prompt Engineering

Architectural Leadership

Tools

Claude

OpenAI

LangChain

LangGraph

Azure

AWS

GCP

Job description

• Lead the design of enterprise-grade GenAI and agentic architectures (single-agent, multi-agent, tool-driven systems).
• Define reference architectures, reusable frameworks, and best practices for LLM applications across the organization.
• Architect and oversee implementation of end-to-end RAG pipelines: Data ingestion → chunking → embeddings → vector search → orchestration → response synthesis.
• Drive scalability, reliability, cost optimization, and performance across GenAI platforms.
• Provide technical leadership in prompt engineering, prompt orchestration, and agent workflows.
• Mentor and guide architects, engineers, and data scientists.

Requirements

• 15+ years of total experience in Data Engineering / Data Science / AI
• 3+ years of hands-on experience in LLM / GenAI solutions at scale
• Proven experience in architecture, solution design, and enterprise delivery
• Strong hands‑on experience with LLMs (Claude, OpenAI, etc.)
• Experience with LangChain, LangGraph, or similar frameworks
• Strong Python/Pyspark engineering expertise with proven API integration experience
• Deep data analysis experience and handling large volume of data
• Prior experience in Data Engineering (ETL/ELT, pipelines, orchestration)
• Good exposure to Cloud platforms (Azure/AWS/GCP)

Core Competencies

Demonstrates extensive expertise in architecting and implementing enterprise-grade GenAI solutions, with a strong focus on LLM applications, data engineering, and cloud platforms. Proven ability to lead technical teams and optimize performance across complex data pipelines.

Highest-signal resume keywords

• 15+ Years Experience in Data Engineering / Data Science / AI
• 3+ Years Hands-On Experience in LLM / GenAI Solutions
• Strong Python/Pyspark Engineering Expertise
• Experience with LangChain or Similar Frameworks
• Technical Leadership in Prompt Engineering

Hard Skills

• Data Engineering
• Data Science
• LLM Solutions
• Architecture Design
• API Integration
• Data Analysis
• ETL/ELT Pipelines
• Prompt Engineering
• GenAI Architectures
• Performance Optimization

Soft Skills

• Mentoring
• Guidance

Industry Keywords

• Enterprise Delivery
• Reference Architectures
• Reusable Frameworks
• RAG Pipelines
• Data Ingestion
• Chunking
• Embeddings
• Vector Search
• Orchestration
• Response Synthesis

Tools & Technologies

• Claude
• OpenAI
• LangChain
• LangGraph
• Azure
• AWS
• GCP