Machine Learning Engineer

Responsibilities

• Design, build, and optimize low-latency inference systems for production machine learning workloads.
• Profile model inference pipelines across execution, runtime configuration, batching, memory movement, and I/O.
• Evaluate, integrate, and tune inference runtime systems to improve latency, throughput, and GPU utilization.
• Build and support benchmarking and profiling tools to compare model variants, hardware targets, and deployment strategies.
• Debug performance issues involving GPU memory, compute saturation, kernel behavior, and CPU/GPU coordination.
• Collaborate with quantitative researchers to shape model and system design for efficient production deployment.

Requirements

• Experience deploying, optimizing, or operating machine learning inference workloads in production environments.
• Proficiency in Python, Java, or C#.
• Experience with at least one systems language such as C, C++, Rust, or Go.
• Solid understanding of modern ML frameworks like PyTorch, including model execution, export, and profiling.
• Ability to reason about latency, throughput, batching, memory use, and GPU utilization under real workloads.

Preferred Qualifications

• Experience with model optimization techniques such as quantization, pruning, distillation, or operator fusion.
• Exposure to low-level GPU programming tools like CUDA, Triton, ROCm, PTX, or CUTLASS.
• Experience running inference workloads on Kubernetes or GPU clusters.
• Background in mathematics, physics, computer science, engineering, or quantitative finance.
• Demonstrated ability to improve real-world inference performance beyond baseline framework implementations.

About the Company

Susquehanna International Group (SIG) is a global quantitative trading firm. This role sits at the intersection of machine learning, systems engineering, and GPU performance, focusing on high-performance model serving systems.