Lead AI Engineer

Seeburger; Chennai District; Hybrid; INR 3,000,000 - 6,000,000; Full time

Job summary

Seeburger Chennai invites a Lead Engineer AI to build production-grade AI features for enterprise systems, leveraging LLMs, orchestration frameworks, and microservices.

You will implement RAG pipelines with vector databases, develop Java/Spring Boot microservices, work with PostgreSQL/MySQL, and ensure observability with OpenTelemetry while optimizing costs.

This hands-on role requires strong English communication and pragmatic problem solving in a fast-paced environment.

Qualifications

• 9+ years of software engineering experience.
• Minimum 2+ years in applied AI/LLM systems.
• Strong Java and Spring Boot expertise.

Responsibilities

• Build AI-powered features for automation and recommendations.
• Develop natural language interfaces for enterprise workflows.
• Integrate LLM APIs (OpenAI, Azure OpenAI, Anthropic).
• Design orchestration workflows using LangChain and LangGraph.
• Implement RAG pipelines with vector databases.
• Develop microservices with Java/Spring Boot.
• Work with SQL databases (PostgreSQL, MySQL).
• Enable observability using OpenTelemetry.
• Ensure cost optimization and performance tuning.

Skills

Java

Spring Boot

Microservices

Python (AI ecosystem)

LLM integration

Prompt engineering

RAG pipelines

Vector databases

PostgreSQL

MySQL

Kafka

OpenTelemetry

AWS

Docker

Kubernetes

Tools

LangChain

LangGraph

Spring AI

Job description

Job Description: Lead Engineer AI

Role Overview

• Hands-on engineering role focused on building AI-enabled enterprise features
• Work with LLMs, orchestration frameworks, and microservices architecture
• Deliver production-grade AI solutions integrated into enterprise systems.

Key Responsibilities

• Build AI-powered features such as automation and intelligent recommendations
• Develop natural language interfaces for enterprise workflows
• Integrate LLM APIs (OpenAI, Azure OpenAI, Anthropic)
• Design orchestration workflows using LangChain, LangGraph, Spring AI
• Implement RAG pipelines with vector databases (PGVector, Pinecone, Weaviate, FAISS)
• Develop microservices using Java, Spring Boot
• Work with SQL databases (PostgreSQL, MySQL)
• Implement event-driven systems using Kafka
• Enable observability using OpenTelemetry
• Ensure cost optimization, guardrails, and performance tuning.

Required Skills

• Strong Java, Spring Boot, Microservices expertise
• Working knowledge of Python (AI ecosystem)
• Experience with LLM integration and prompt engineering
• Hands-on with RAG pipelines and vector databases
• SQL expertise (PostgreSQL, MySQL)
• Kafka and event-driven architecture
• AWS, Docker, Kubernetes basics
• Monitoring using Open Telemetry.

Experience

• 9 -14 years of software engineering experience
• Minimum 2+ years in applied AI / LLM systems