Senior Software Engineer – C++/Python & GPU Computing

Are you passionate about AI/ML, distributed systems, and high-performance computing? Join a team working on cutting-edge technologies to optimize AI inference across multi-GPU and multi-node environments.

🔹 What you will do

• Enable and benchmark AI models on large-scale distributed systems, evaluating performance, accuracy, and scalability.
• Optimize AI workloads across multi-GPU and multi-node configurations.
• Develop parallelization strategies to improve throughput and reduce latency.
• Analyze performance bottlenecks and investigate scalability challenges.
• Build and maintain benchmarking pipelines, monitoring frameworks, and real-time performance dashboards.
• Collaborate with software and GPU library teams to improve distributed AI workloads.
• Contribute to model management systems, technical documentation, and automated testing.

🔹 Required experience

• Strong hands-on programming skills in C/C++ and Python.
• Experience in software design, debugging, performance analysis, and test development.
• Knowledge of distributed systems and large-scale compute clusters.
• Familiarity with GitHub, Jenkins, or similar CI/CD tools.
• Advanced English proficiency (C1).

🔹 Nice to have

• Experience with AI inference and serving frameworks such as vLLM, SGLang, or llama.cpp.
• Knowledge of KV cache transfer technologies such as Mooncake or NIXL/RIXL.
• Familiarity with expert parallelization approaches such as DeepEP, MORI, or PPLX-Garden.
• Experience with SLURM and Kubernetes.
• Master’s or PhD in Computer Science, Computer Engineering, or a related field, or equivalent practical experience.

🔹 What we are looking for A technically strong engineer with excellent problem-solving skills, a passion for performance optimization, and the ability to take ownership of complex engineering challenges in collaborative and independent environments.

Interested in pushing the boundaries of distributed AI performance?

📩 Apply now or contact me for more details!