Backend Integration Engineer

AVIX Labs; Chennai District; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

AVIX Labs is seeking an AI/ML Engineer in Chennai to design, develop, and deploy AI-powered applications using LLMs and retrieval-based systems. The role involves building scalable backend services and optimizing AI workloads.

You will work with LangChain, LlamaIndex, and vector embeddings, and collaborate with product teams to convert business needs into AI workflows. Proficiency in Python and AWS is required, with hands-on experience in FastAPI or similar frameworks.

Qualifications

• Proficiency in Python with hands-on experience.
• Experience with FastAPI or similar web frameworks.
• Hands-on experience with LangChain or LlamaIndex.
• Strong understanding of vector databases and embeddings.
• Familiarity with AWS cloud services.

Responsibilities

• Design and implement LLM-based applications (RAG, copilots, AI assistants).
• Build data pipelines for embeddings, retrieval, and indexing.
• Integrate AI models with backend systems using FastAPI or Node.js.
• Optimize performance, latency, and cost of AI solutions.
• Collaborate with product and engineering teams to translate business needs into AI workflows.

Skills

Python

FastAPI

LangChain

LlamaIndex

Vector embeddings

AWS services

Job description

Job Description

The AI/ML Engineer will design, develop, and deploy AI-powered applications focused on real-world business use cases. This role involves working with large language models, building retrieval-based systems, and integrating AI into scalable backend services.

Responsibilities

• Design and implement LLM-based applications (RAG, copilots, AI assistants)
• Build data pipelines for embeddings, retrieval, and indexing
• Integrate AI models with backend systems using FastAPI or Node.js
• Optimize performance, latency, and cost of AI solutions
• Collaborate with product and engineering teams to translate business needs into AI workflows

Qualifications

• Strong proficiency in Python
• Experience with FastAPI or similar frameworks
• Hands-on experience with LLM frameworks (LangChain, LlamaIndex)
• Understanding of vector databases and embeddings
• Familiarity with AWS services

Additional Requirements

• Experience with fine-tuning or prompt engineering is a plus
• Understanding of multi-agent systems is an advantage