Software Engineer / AI Engineer (MERN Stack & LLM Fine-Tuning)

Role Overview

Infactra AI is an Enterprise AI platform that helps organizations automate workflows, deploy AI Agents, integrate with ERP/CRM systems, and build secure AI solutions for enterprises. We are looking for a passionate Software Engineer / AI Engineer with expertise in the MERN Stack and Generative AI to build scalable web applications, integrate LLMs, fine-tune open-source models, and develop AI-powered enterprise applications.

Responsibilities

• Develop scalable web applications using the MERN Stack (MongoDB, Express.js, React.js, Node.js).
• Design and build REST APIs and microservices.
• Integrate OpenAI, Llama, Qwen, Mistral, DeepSeek, or other LLMs into enterprise applications.
• Fine-tune open-source language models using enterprise datasets.
• Build Retrieval-Augmented Generation (RAG) pipelines with vector databases.
• Develop AI Agents for workflow automation and enterprise productivity.
• Implement prompt engineering, evaluation, and model optimization.
• Work with embeddings, semantic search, and document indexing.
• Deploy AI models using Docker, Kubernetes, or cloud platforms.
• Integrate AI solutions with ERP, CRM, and business applications.
• Optimize application performance, scalability, and security.
• Collaborate with product, design, and business teams to deliver AI solutions.

Requirements

• MongoDB, Express.js, React.js, Node.js, TypeScript, or JavaScript.
• Python, PyTorch, or TensorFlow.
• Experience with Hugging Face Transformers, PEFT, LoRA, or QLoRA.
• Knowledge of RAG Architecture and LangChain or LlamaIndex.
• Experience with Vector Databases (Pinecone, Qdrant, ChromaDB, Milvus, or FAISS).
• Familiarity with Docker and Kubernetes.
• Bachelor's or Master's degree in Computer Science, AI, or a related field.
• 2–5 years of software engineering experience.

Skills

• MERN Stack
• Generative AI
• Python
• LLM Fine-Tuning
• Vector Databases

Bonus Skills

• MCP (Model Context Protocol)
• Multi-Agent Systems
• Computer Vision
• NVIDIA GPU optimization
• ONNX / TensorRT