ML Inference Performance Engineer — Ultra-Low Latency

Priorslab

New York (NY)

Hybrid

USD 200.000 - 300.000

Vollzeit

14 Tage+

Erhalte eine Antwort von diesem Arbeitgeber

Dein Lebenslauf und dein Anschreiben, genau auf das zugeschnitten, was gesucht wird.

Schaffe es an den ATS-Filtern vorbei

Benefits dieser Stelle

Hybrid working opportunities
Free breakfast, lunch, and snacks
Wellness reimbursement
Team sports and events
Learning and development opportunities

Zusammenfassung

Tower Research Capital is seeking a talented engineer to bridge quantitative research and production ML inference. You will architect inference pipelines reaching microsecond latency, optimizing across CPUs, GPUs, and FPGAs within a high-performance trading environment.

Responsibilities include platform evaluation, memory subsystem optimization, and cross-functional collaboration with ML researchers and HPC teams to deploy latency-critical strategies.

Qualifikationen

  • 2+ years optimizing deep learning inference in latency-sensitive environments.
  • Strong Python/C++ skills with experience in mixed-precision computing.
  • Proven GPU kernel development experience and use of optimization libraries.
  • Familiarity with Triton, TensorRT, ONNX, and profiling tools.
  • Deep GPU microarchitecture knowledge and cross-architecture benchmarking.
  • Bonus: experience with FPGAs/ASICs and financial trading context.

Aufgaben

  • Lead evaluation of inference platforms (CPUs/GPUs/FPGAs) for deployment decisions.
  • Analyze memory hierarchies and interconnect bottlenecks to improve latency.
  • Collaborate with Infrastructure to design latency-critical inference strategies.
  • Develop highly optimized GPU kernels and integrate performance libraries.
  • Implement model reduction techniques for low-latency, event-level inference.
  • Work with ML Researchers, HPC and Datacenter Engineers to realize deployments.

Kenntnisse

Python
C++
PyTorch
JAX
GPU kernel development
TensorRT
Triton
Nsight profiling

Tools

CUDA
cuBLAS
CUTLASS
TensorRT
ONNX
IREE
HLS4ML
Nsight Systems
Nsight Compute

Jobbeschreibung

Tower Research Capital is seeking a talented engineer to bridge quantitative research and production ML inference. You will architect inference pipelines reaching microsecond latency, optimizing across CPUs, GPUs, and FPGAs within a high-performance trading environment.

Responsibilities include platform evaluation, memory subsystem optimization, and cross-functional collaboration with ML researchers and HPC teams to deploy latency-critical strategies.

Hol dir deinen kostenlosen, vertraulichen Lebenslauf-Check.

oder ziehe deine Datei hierhin.

Similar jobs

Ähnliche Jobs, die dir auch gefallen könnten

Low-Latency ML Inference Engineer
Low-Latency ML Inference Engineer

Career Techniques • New York (NY)

Hybrid
USD 200.000 - 300.000
Low-Latency ML Inference Engineer
Low-Latency ML Inference Engineer

Susquehanna International Group, LLP • Bala Cynwyd (PA)

Vor Ort
USD 150.000 - 230.000
Machine Learning Performance Engineer (Inference)
Machine Learning Performance Engineer (Inference)

Priorslab • New York (NY)

Hybrid
USD 200.000 - 300.000
Hybrid working opportunities
Free breakfast, lunch, and snacks
Wellness reimbursement
+2
Machine Learning Performance Engineer (Inference)
Machine Learning Performance Engineer (Inference)

Career Techniques • New York (NY)

Vor Ort
USD 200.000 - 300.000
Senior ML Engineer - Production Inference & Low-Latency AI
Senior ML Engineer - Production Inference & Low-Latency AI

Cloudflare, Inc. • New York (NY)

Hybrid
USD 194.000 - 266.000
Medical Insurance
Dental Insurance
Vision Insurance
+2
Low-Latency ML Inference Engineer (GPU/ Production)
Low-Latency ML Inference Engineer (GPU/ Production)

Priorslab • Bala Cynwyd (PA)

Vor Ort
USD 150.000 - 210.000
GPU Systems Engineer - Low-Latency HPC & AI Clusters
GPU Systems Engineer - Low-Latency HPC & AI Clusters

Tower Research Capital • New York (NY)

Vor Ort
USD 200.000 - 300.000
Generous paid time off policies
Hybrid working opportunities
Free breakfast, lunch & snacks
+4
Low-Latency Quant Dev Intern - Summer 2027
Low-Latency Quant Dev Intern - Summer 2027

Tradermath • New York (NY)

Hybrid
USD 182.000 - 296.000
Housing accommodation
Free breakfast, lunch, and snacks
Networking events
ML Research Platform Engineer
ML Research Platform Engineer

Tower Research Capital • New York (NY)

Hybrid
USD 200.000 - 300.000
Hybrid working opportunities
Generous PTO
Free meals in office
Machine Learning Engineer- Inference Optimization | Experienced Hire
Machine Learning Engineer- Inference Optimization | Experienced Hire

Susquehanna International Group, LLP • Bala Cynwyd (PA)

Vor Ort
USD 150.000 - 230.000