We are seeking an experienced AI Infrastructure & Automation Engineer to join our team. In this role, you will be the bridge between high-level AI application logic and the underlying hardware that powers it. You will own the responsibility of scaling our AI operations, ensuring our LLM workflows run efficiently on centralized GPU infrastructure, and automating our backend systems. If you have a passion for building robust AI pipelines and optimizing server performance, we want to hear from you.
Key Responsibilities
- Infrastructure Management: Architect, deploy, and maintain centralized GPU server clusters to ensure high availability and performance for LLM training and inference.
- LLM Integration: Develop and maintain backend logic to integrate Large Language Models (LLMs) into production-grade applications.
- Automation: Build end-to-end automation workflows that reduce manual operational tasks, utilizing tools like N8N, Make, or custom Python scripts.
- System Optimization: Monitor and tune server resources to maximize GPU utilization and minimize inference latency.
- Pipeline Development: Create and manage data pipelines for ingestion, preprocessing, and model fine-tuning.
- Scalability: Troubleshoot hardware/software bottlenecks and scale our infrastructure as our AI service demand grows.
Required Qualifications
- Deep Technical Expertise: 3+ years of experience in AI/ML infrastructure, systems engineering, or a similar technical role.
- GPU & Server Knowledge: Hands-on experience with managing GPU-accelerated servers (e.g., NVIDIA stack, CUDA, and containerization with Docker/Kubernetes).
- LLM Proficiency: Practical experience with deploying and fine-tuning LLMs (e.g., Llama, OpenAI API, Mistral) in production environments.
- Programming: Strong proficiency in Python and experience with MLOps frameworks.
- System Integration: Proven ability to connect APIs, webhooks, and databases to build cohesive, automated business workflows.
- Problem-Solving: A "builder" mindset with the ability to identify infrastructure bottlenecks and implement solutions proactively.
Job Type: Full-time
Pay: Rs80,000.00 - Rs120,000.00 per month
Work Location: In person