🛠 Tech Stack

💼 About This Role

You'll develop and optimize a high-performance AI inference framework for large-scale distributed environments. You'll work on low-level system components leveraging GPU acceleration and RDMA networking. This role offers exposure to cutting-edge supercomputing and AI infrastructure.

🎯 What You'll Do

• Develop and optimize a high-performance AI inference framework
• Work on low-level system components with GPU kernels and hardware offloads
• Analyze and improve system performance through benchmarking and profiling
• Collaborate with cross-functional engineering teams on scalable infrastructure

📋 Requirements

• 8+ years of experience in modern C, C++, or Rust development
• Strong experience in Linux environments with debugging tools
• Deep understanding of TCP/IP networking, OS, and computer architecture
• Proven ability to work on low-level software with performance focus

✨ Nice to Have

• Experience with CUDA kernels or LLM inference systems
• Exposure to HPC, parallel programming, or RDMA technologies
• Experience with distributed storage technologies

🎁 Benefits & Perks

• 💰 Competitive compensation with performance-based rewards
• 🏥 Comprehensive benefits for health, wellbeing, work-life balance
• 🌍 Remote options in Switzerland
• 🤝 Collaboration with top-tier engineering talent
• 📈 Focus on technical excellence and career growth

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Team Interview· 45 min