🛠 Tech Stack

💼 About This Role

You'll design and operate production-grade ML inference infrastructure powering real-time AI applications in a fast-scaling cloud startup. Core impact: building scalable, reliable, cost-efficient systems for GPU-based model serving at low latency.

🎯 What You'll Do

• Build and operate production-grade model serving infrastructure with vLLM, TGI, or Triton
• Design and implement blue/green and canary deployment pipelines for ML models
• Develop auto-scaling systems and multi-model serving architectures
• Optimize GPU utilization, memory efficiency, and network throughput

📋 Requirements

• 4+ years of experience in ML Ops or similar infrastructure roles
• Hands-on experience with model serving frameworks like vLLM, TGI, or Triton
• Strong background in container orchestration and GPU workloads in production
• Proficiency in Python and infrastructure-as-code tools like Terraform or Helm

✨ Nice to Have

• Experience with ML platforms like Kubeflow or MLflow
• Knowledge of CUDA/ROCm optimization or multi-tenant inference systems
• Background in early-stage startups or greenfield infrastructure projects

🎁 Benefits & Perks

• 🏖️ Remote work from anywhere in EMEA
• 💰 Competitive equity in a well-funded startup
• 🚀 Own critical infrastructure from the ground up
• 🧠 Deep expertise in next-gen AI infrastructure

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3System Design Interview· 60 min