GenAI Backend Engineer (Python, LLMs, RAG)

Mphasis; Berkeley Heights (NJ); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Onsite work from Day 1

Job summary

Mphasis is seeking a Python AI Developer with hands-on experience building production-grade Generative AI applications, including RAG solutions, AI agents, backend APIs, and microservices.

You will deeply leverage Python to integrate LLMs with enterprise applications, vector databases, and external APIs, and you will build scalable backend services using FastAPI/Flask/Django. Dockerized deployments to AWS/Azure/GCP and MLOps practices are expected.

Qualifications

• Strong Python expertise with production-grade GenAI applications.
• Experience integrating LLMs with enterprise apps, vector databases, and external APIs.
• Hands-on in AI/GenAI, RAG solutions, and AI agents.

Responsibilities

• Design and develop AI/GenAI-driven applications using Python.
• Build scalable backend APIs, microservices, and data pipelines.
• Develop and implement Retrieval-Augmented Generation (RAG) solutions.
• Build and orchestrate AI/LLM agents using LangChain, LangGraph, CrewAI, or similar frameworks.
• Integrate LLMs with enterprise applications, vector databases, and REST APIs.
• Implement prompt engineering and NLP solutions for enterprise use cases.
• Develop backend services using FastAPI, Flask, or Django.
• Optimize application performance and build production-ready solutions.
• Containerize applications using Docker and support deployment to AWS, Azure, or GCP.
• Follow software engineering and MLOps practices including Git/version control, CI/CD, testing, monitoring, and deployment.

Skills

Python programming

GenAI development

LLM integration

NLP

REST APIs

Tools

LangChain

LangGraph

CrewAI

FastAPI

Flask

Django

Docker

Job description

Mphasis is seeking a Python AI Developer with hands-on experience building production-grade Generative AI applications, including RAG solutions, AI agents, backend APIs, and microservices.

You will deeply leverage Python to integrate LLMs with enterprise applications, vector databases, and external APIs, and you will build scalable backend services using FastAPI/Flask/Django. Dockerized deployments to AWS/Azure/GCP and MLOps practices are expected.