AI Infrastructure Engineer (GPU) - Remote

Overview

Pragmatike is recruiting on behalf of a fast-scaling, well-funded distributed cloud infrastructure startup building next-generation AI-native cloud services. The company is redefining how compute is delivered by providing GPU-powered infrastructure for AI/ML workloads, secure storage, and high-speed data transfer through a decentralized architecture that significantly reduces environmental impact compared to traditional cloud providers.

In Short

• Fully remote position for an AI Infrastructure Engineer focused on GPU technologies.
• Design and operate production-grade model serving infrastructure.
• Work with ML inference platforms powering real-time AI applications.
• Optimize GPU utilization and model artifact storage performance.
• Implement deployment pipelines for ML models.
• Manage CI/CD pipelines for automated model deployments.
• Strong emphasis on production reliability and performance tuning.
• Ownership of the full lifecycle of ML systems.
• Collaborate with cross-functional teams to ensure system health.
• Opportunity to influence core engineering decisions.

Requirements

• 4+ years of experience in ML Ops or similar roles.
• Hands-on experience with model serving frameworks like vLLM, TGI, Triton.
• Strong background in container orchestration and GPU workloads.
• Proficiency in Python and infrastructure-as-code tools.
• Experience with MLOps tooling and automated deployment pipelines.
• Understanding of distributed systems and production reliability.
• Ability to work independently in a remote environment.
• Effective use of AI coding assistants for development.

Benefits

• Ownership of critical infrastructure in a scaling AI-native cloud platform.
• Build foundational ML inference systems from the ground up.
• Gain expertise in next-generation AI infrastructure.
• Influence core engineering decisions and define best practices.
• Work in a high-growth, well-funded startup environment.