🛠 Tech Stack

💼 About This Role

You'll benchmark and optimize GPU platforms for large-scale AI workloads, working at the intersection of deep learning optimization and cloud-scale infrastructure. Contribute directly to improving performance and efficiency of cutting-edge AI systems. This role offers exposure to modern AI frameworks and international collaboration.

🎯 What You'll Do

• Benchmark GPU performance for ML and AI workloads across architectures
• Profile GPU performance at system and kernel levels for optimization
• Analyze and debug training/inference workloads for efficiency and scalability
• Develop internal tools and dashboards for performance metrics

📋 Requirements

• Strong foundation in machine learning and deep learning architectures
• Deep understanding of performance optimization for neural network training/inference
• Extensive experience with PyTorch, JAX, or TensorRT-LLM
• Solid expertise with CUDA, NCCL, and GPU software stacks

✨ Nice to Have

• Experience with LLM inference frameworks like vLLM or SGLang
• Familiarity with cloud ML ecosystems (AWS, GCP, Azure ML)
• Contributions to open-source ML tooling or benchmarking

🎁 Benefits & Perks

• 💰 Competitive compensation aligned with experience
• 🏡 Flexible remote work
• 📚 Continuous learning and career development
• 🌍 International work environment with global teams
• 🔬 Impactful AI projects shaping ML infrastructure

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

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