Lead Al Engineer

Luna Bearings; Hyderabad; On-site; INR 4,000,000 - 5,500,000; Full time

Job summary

Luna Bearings in Hyderabad seeks a Lead AI Engineer to architect and scale enterprise AI infrastructure, focusing on RAG frameworks, LLM gateways, and agentic workflows. You will ensure robust data pipelines and seamless AWS-based deployments.

You will mentor engineers, shape design patterns, and guide end-to-end system deployment across cloud environments, delivering scalable, structured AI solutions for enterprise needs.

Qualifications

• 5–8 years of professional software engineering experience.
• Hands-on expertise in Java and the Spring Boot framework.
• Python for AI/ML integrations and scripting.
• Strong knowledge of relational and NoSQL databases (PostgreSQL, MySQL, MongoDB).
• Experience with AWS cloud services and containerized deployments.
• Experience building scalable RAG applications and LLM orchestration layers.

Responsibilities

• AI Architecture & Strategy: Lead architectural oversight for content ingestion and enrichment pipelines.
• RAG & LLM Integration: Design, deploy, and optimize RAG frameworks and LLM gateways.
• Agentic Workflows: Build and orchestrate multi-agent platforms and workflows.
• Protocol Implementation: Drive Model Context Protocol standardization across systems.
• Data Pipeline Engineering: Architect reliable LLM generation pipelines with structured JSON validation.
• Technical Leadership & System Design: Mentor teams and guide cloud deployment strategies.

Skills

Java

Spring Boot

Python

OO design

AWS

Tools

PostgreSQL

MySQL

MongoDB

JSON Schema

Job description

Job Title: Lead AI Engineer

Location: Hyderabad

About theRole:

We are seeking an experienced Lead AI Engineerto architect, develop, and scale our enterprise AI infrastructure and contentprocessing pipelines. You will lead the technical design of AI systems,focusing on Retrieval-Augmented Generation (RAG) frameworks, LLM gateways, andintelligent agentic workflows. As a technical leader, you will ensure our AIdata pipelines are robust, highly structured, and seamlessly integrated intoour AWS cloud ecosystem.

In this role you will...

• AI Architecture & Strategy: Lead the architectural oversight and technical direction for content ingestion and enrichment pipelines, ensuring scalable and efficient AI integrations.
• RAG & LLM Integration: Design, deploy, and optimize advanced Retrieval-Augmented Generation (RAG) frameworks and centralized LLM gateways.
• Agentic Workflows: Build and orchestrate multi-agent platforms and workflows using modern AI integration frameworks.
• Protocol Implementation: Drive the implementation of Model Context Protocol (MCP) to standardize and streamline interactions between foundation models and enterprise backend systems.
• Data Pipeline Engineering: Architect highly reliable LLM generation pipelines, enforcing strict structured JSON outputs to guarantee schema validation and application parsing stability.
• Technical Leadership & System Design: Mentor engineering teams, apply best-in-class software design patterns, and guide infrastructure deployment planning across cloud environments.

You'vegot what it takes if you have...

• Experience: 5-8 years of professional software engineering experience, with a proven track record of designing and deploying enterprise-grade systems and AI platforms.
• Programming & Frameworks (Mandatory): Deep, hands-on expertise in Java and the Spring / Spring Boot framework.
• Good working knowledge of Python is also required for AI/ML integrations and scripting.
• Database Expertise (Mandatory): Strong knowledge of both relational databases (RDBMS such as PostgreSQL or MySQL) and NoSQL databases, specifically MongoDB.
• Design Patterns (Mandatory): Extensive knowledge of object-oriented design, architectural design patterns, and enterprise integration patterns for building scalable, decoupled systems.
• Cloud Infrastructure (Mandatory): Hands-on experience with AWS cloud services, including the deployment, scaling, and management of containerized applications and data pipelines.
• AI/ML Expertise: Practical experience building scalable RAG applications, vector search optimizations, and LLM orchestration layers.
• Data Engineering: Proven ability to build resilient data ingestion workflows with a strong emphasis on JSON-based structured data validation over legacy text formats.

Good to have skills...

• Familiarity with enterprise AI toolkits (such as Google ADK).
• Experience managing regional infrastructure rollouts and navigating model availability constraints across different deployment stages.

#LI-Onsite