Low-Latency ML Inference Engineer

Susquehanna International; Bala Cynwyd (PA); On-site; USD 150,000 - 230,000; Full time

Job summary

Susquehanna International is seeking a Machine Learning Engineer focused on low-latency inference optimization to help build, tune, and productionize high-performance model serving systems. The role sits at the intersection of ML, systems engineering, and GPU performance, addressing latency, throughput, reliability, and hardware efficiency in production environments.

You will work closely with quantitative researchers and engineers to identify bottlenecks, evaluate frameworks, and shape

Qualifications

• Experience deploying ML inference in production.
• Proficient in Python and at least one systems language (C/C++, Rust, or Go).
• Strong understanding of ML frameworks (e.g., PyTorch) and performance profiling.

Responsibilities

• Design, build, and optimize low-latency inference systems for production ML workloads.
• Profile inference pipelines across execution, batching, memory, networking, and I/O.
• Evaluate and tune inference runtime systems and frameworks.
• Improve latency, throughput, and GPU utilization in production workloads.
• Build tooling for benchmarking and profiling model variants and deployments.
• Debug performance issues related to GPU memory, kernel behavior, and data movement.

Skills

Python

C/C++

Java

Rust/Go

PyTorch

CUDA

Kubernetes

Tools

PyTorch

CUDA

Triton

Kubernetes

Job description

Susquehanna International is seeking a Machine Learning Engineer focused on low-latency inference optimization to help build, tune, and productionize high-performance model serving systems. The role sits at the intersection of ML, systems engineering, and GPU performance, addressing latency, throughput, reliability, and hardware efficiency in production environments.

You will work closely with quantitative researchers and engineers to identify bottlenecks, evaluate frameworks, and shape