Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$209к$250кмедиана$300к
50 в выборке
На СНГ рынке: $5.3к/мес ($3.9к - $6к)
88
Крутая вакансия
развернуть
Чёткий фокус на ускорении production-инференса, практическая работа с GPU-системами и взаимодействие с количественными командами делают роль сильной; при этом работа только на месте, а льготы и перспективы роста не описаны.
Чёткие задачи
Современный стек
Финансовые технологии
?Работа в офисе
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Machine Learning Engineer (Inference Optimization) (PyTorch/GPU): Building and optimizing low-latency inference systems for production machine learning workloads with an accent on model serving, GPU performance, and runtime optimization. Focus on profiling execution pipelines, improving latency and throughput, and designing efficient deployment strategies for transformer-style models under real-world hardware constraints.
Location: Bala Cynwyd (Philadelphia Area), Pennsylvania, United States
Company
hirify.global, LLP.
What you will do
Design, build, and optimize low-latency inference systems for production machine learning workloads.
Profile inference pipelines across model execution, runtime configuration, batching, memory movement, serialization, networking, and I/O.
Evaluate, integrate, and tune inference runtime, serving, and compilation systems.
Improve latency, throughput, and GPU utilization while building benchmarking and profiling tools for model, hardware, and deployment comparisons.
Debug GPU memory, compute saturation, kernel behavior, CPU/GPU coordination, data movement, and serving-layer performance issues.
Collaborate with quantitative researchers, engineers, and lower-level GPU specialists to make research models efficient for production deployment.
Requirements
Experience deploying, optimizing, or operating machine learning inference workloads in production or production-like environments.
Programming experience in Python, Java, C#, or similar, plus at least one systems language such as C, C++, Rust, or Go.
Solid understanding of modern machine learning frameworks such as PyTorch, including model execution, export, tracing, compilation, and performance profiling.
Ability to reason about latency, throughput, batching, memory use, GPU utilization, and reliability under real workloads.
Strong practical judgment when balancing model quality, latency, throughput, implementation complexity, and maintainability.
Nice to have
Experience optimizing inference for latency-sensitive or high-throughput applications.
Experience with quantization, pruning, distillation, operator fusion, graph lowering, custom operators, or model compilation.
Exposure to CUDA, Triton language, ROCm, PTX, CuTe, CUTLASS, FlashInfer, or similar low-level GPU programming tools.
Experience running inference workloads on Kubernetes or GPU clusters, including scheduling, autoscaling, observability, and resource management.
Background in mathematics, physics, computer science, engineering, statistics, quantitative finance, or another technical field.
Demonstrated ability to improve real-world inference performance beyond a baseline framework implementation.
Culture & Benefits
Immediate start.
Work closely with quantitative researchers and engineers on production machine learning systems.
Hiring process
Recruiting agencies may contact recruiting@sig.com to discuss a partnership.
Resumes or referrals submitted without a signed agency agreement are not eligible for an agency fee.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →