🛠 Tech Stack

💼 About This Role

You'll deploy scalable ML services and manage Kubernetes clusters for a decentralized AI protocol. You'll optimize GPU resources and integrate advanced ML techniques like LoRA. This role allows you to work on decentralized inference and multi-agent systems at a research-driven company.

🎯 What You'll Do

• Deploy scalable ML services with auto-scaling Kubernetes clusters.
• Optimize GPU resources using MIG and NOS.
• Manage cloud storage for high availability and performance.
• Integrate LoRA and model merging into workflows.

📋 Requirements

• Proficiency in Kubernetes, Helm, and containerization.
• GPU optimization experience (MIG, NOS) and cloud platforms.
• Strong knowledge of monitoring (Grafana, Prometheus) and scripting (Python, Bash).
• Hands-on experience with CI/CD tools and workflow management.

✨ Nice to Have

• 5+ years in MLOps or ML engineering.
• Experience with advanced ML techniques like multi-sampling.
• Proficiency in Go or Rust.

🎁 Benefits & Perks

• 🔬 Meaningful AI Research on decentralized inference and multi-agent systems.
• 🌍 Scalable and Sustainable AI reducing reliance on massive compute clusters.
• 🤝 Highly Technical Team of experienced engineers and researchers.