We are looking for a Full-Stack Machine Learning & MLOps Engineer who can work across the entire AI product stack, from local GPU infrastructure and model serving to backend AI systems and modern frontend applications.

You will be the core orchestrator - build and operate local AI inference and RAG infrastructure, develop high-performance Python/FastAPI services, integrate vector databases and AI pipelines, and create intuitive React/Next.js interfaces for AI-powered applications.

This is a highly hands-on engineering role for someone who understands that production AI requires much more than simply calling an API.

AI / ML Infrastructure

- Deploy, manage, and optimize locally hosted open-weight LLMs and AI models using inference engines such as vLLM, Ollama, and similar technologies, with a focus on GPU utilization, memory management, inference performance, and model serving.
- Work with model optimization and quantization techniques such as AWQ and GGUF, while monitoring and troubleshooting GPU, inference, and system-level performance.

MLOps & Containerization

- Build and manage Docker/Docker Compose environments connecting LLM inference engines, vector databases, backend services, and supporting infrastructure.
- Manage Linux-based AI environments and NVIDIA GPU infrastructure, including NVIDIA Container Toolkit, container networking, deployment workflows, and system reliability.

Backend & AI Platform

- Build scalable asynchronous Python/FastAPI services and production-grade AI/RAG systems incorporating hybrid search, embeddings, re-ranking, and vector databases such as Qdrant, Pinecone, or Weaviate.
- Work with PostgreSQL, Redis, and other databases while developing background jobs, queues,



asynchronous processing, and reliable AI workflows.

Backend, Frontend & Full-Stack

- Develop modern AI applications using React/Next.js, including chat-based interfaces capable of handling real-time streaming AI responses.
- Implement SSE, WebSockets, and secure frontend-backend integrations to deliver responsive AI experiences connected to backend services and databases.

ML & AI System

- Work with machine learning, deep learning, and LLM-based systems to evaluate, optimize, deploy, and improve AI models across production applications.
- Prepare and process structured and unstructured datasets, and support embeddings, vector search, RAG, AI agents, model fine-tuning, and evaluation workflows.
- Manage and optimize the bare-metal Linux AI environment, including NVIDIA GPU memory allocation and PagedAttention-based inference, to maintain system stability and prevent GPU Out-of-Memory (OOM) issues during high-context and high-load workloads.

Pay: ₹15,000.00 - ₹25,000.00 per month

Benefits:

- Cell phone reimbursement
- Commuter assistance
- Flexible schedule
- Food provided
- Health insurance
- Internet reimbursement
- Life insurance
- Paid sick time
- Provident Fund
- Work from home

Application Question(s):

- Are you comfortable with performance-based targets and incentives?
- If selected, how soon can you join (in days)?
- Are you currently employed?
- What are your Monthly Stipend Expectations (In INR)?
- Briefly describe your future plans related to Education, Career, and Personal goals.
- Why do you believe you are a solid fit for this role?
- Describe a situation where you took initiative or solved a problem.

Work Location: In person

📌 Full-Stack AI & MLOps Engineer (India)
🏢 CREATIVE IDEA TECHNOLOGY PRIVATE
📍 India