Backend Engineer AIML , LLM Integration

LabourNet; Mysuru, Bengaluru; On-site; INR 2,500,000 - 4,000,000; Full time

Job summary

LabourNet in Mysuru is seeking a skilled Backend Engineer AI/ML to design scalable backend services, integrate LLM APIs and build AI middleware.

You will optimize performance, latency and costs, implement RAG pipelines, vector search, and ensure secure, production-ready implementations across cloud platforms.

Qualifications

• Experience designing and building scalable backend services.
• Proficient in Python, Java, Node.js or TypeScript.
• Hands-on exposure to Anthropic Claude API and LLM integration.
• Experience with prompt engineering for effective AI responses.
• Familiarity with RAG architecture and vector databases.

Responsibilities

• Design and develop scalable backend services, microservices and REST APIs.
• Integrate Claude API and other LLM platforms into applications.
• Build LLM-powered backend services and AI orchestration workflows.
• Implement RAG pipelines, embeddings and semantic search.
• Work with vector databases for document storage and retrieval.
• Develop prompt engineering strategies and optimize LLM responses.
• Implement document ingestion, chunking and retrieval workflows.
• Optimize AI applications for performance, latency and cost.
• Ensure API security, data privacy and application scalability.
• Collaborate with cross-functional teams to deliver production-ready AI solutions.

Skills

Backend development

Python

Java

Node.js

TypeScript

Claude API

LLM integration

Prompt engineering

RAG architecture

Vector databases

REST APIs

Microservices

Cloud exposure

Tools

Pinecone

Qdrant

Chroma

FAISS

Weaviate

Milvus

Job description

Job Description

We are looking for a skilled Backend Engineer AI/ML with strong experience in backend development and hands-on exposure to Generative AI, Large Language Models (LLMs), Claude API, and RAG-based applications.

The ideal candidate should have experience building scalable backend services, integrating LLM APIs, developing AI middleware, and implementing production-ready AI solutions.

Key Responsibilities

• Design and develop scalable backend services, microservices and REST APIs.
• Integrate Anthropic Claude API and other LLM platforms into applications.
• Build LLM-powered backend services and AI orchestration workflows.
• Implement RAG pipelines, embeddings and semantic search.
• Work with vector databases for document storage and retrieval.
• Develop prompt engineering strategies and optimize LLM responses.
• Implement document ingestion, chunking and retrieval workflows.
• Optimize AI applications for performance, latency and cost.
• Ensure API security, data privacy and application scalability.
• Collaborate with cross-functional teams to deliver production-ready AI solutions.

Mandatory Skills

• Strong backend development experience.
• Python / Java / Node.js / TypeScript.
• Hands-on experience with Anthropic Claude API.
• Generative AI and LLM integration.
• Prompt Engineering.
• RAG Architecture.
• Vector Databases Pinecone, Qdrant, Chroma, FAISS, Weaviate or Milvus.
• REST API and Microservices Development.
• LLM orchestration and backend integration.
• Cloud exposure – AWS / Azure / GCP.