Engineering Lead Manager, Exchange Platform (Real-Time Inference)
Контакты
Формат работы
hybrid
Тип работы
fulltime
Грейд
lead
Английский
b2
Страна
Canada
goteam leadershipbackendmachine learningdistributed systemslow latency systemsreal time systemsinference
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
$109к$123кмедиана$206к
48 в выборке
На СНГ рынке: $5.5к/мес ($4.3к - $7.2к)
87
Крутая вакансия
развернуть
У роли четкая зона ответственности за критичную платформу реального времени и сбалансированное сочетание инженерной работы с руководством командой, но условия оплаты не раскрыты.
Чёткая зона ответственности
Современный стек
?Рекламные технологии
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Engineering Lead Manager, Exchange Platform (Real-Time Inference) (AdTech/ML infrastructure): Leading the development of real-time inference infrastructure for an advertising exchange with an accent on millisecond-level latency, reliability, and safe model deployment. Focus on redesigning hot-path services, enabling internal teams and partners to run models and decisioning logic, and building a high-performing engineering team.
Location: Hybrid in Toronto, 8 Spadina Ave
Company
hirify.global operates an advertising exchange whose platform selects bid requests for DSP partners and supports real-time model and decisioning infrastructure.
What you will do
Own the technical direction and design of real-time inference systems on the exchange hot path.
Lead the evolution of model inference toward millisecond-level performance across the hot path.
Design interfaces and guardrails that allow internal ML teams and future partners to deploy models and decisioning logic safely and independently.
Build, lead, mentor, and grow a distributed engineering team while establishing its operating model and technical direction.
Develop scalable, resilient, observable services and maintain rigorous testing, release, and operational practices.
Partner with offline ML, data science, MLOps, and Exchange Platform teams; track system health, latency, reliability, and performance metrics.
Requirements
Strong software engineering skills with significant Golang experience, or comparable experience with Java, C#, C++, or Rust, and the ability to work hands-on in the codebase.
Significant experience designing, building, testing, and operating complex, high-throughput, low-latency backend systems at scale.
Strong understanding of real-time systems, including latency, concurrency, performance, reliability, and failure modes.
Working understanding of machine learning fundamentals, including training, inference, model deployment, and model serving; real-time ML exposure is an asset.
Track record of owning critical production systems defensively, anticipating risks, and maintaining safe operations.
Excellent leadership and team-building skills, with at least 2 years of experience leading engineering teams or serving as a technical lead.
Excellent problem-solving, communication, cross-team collaboration, negotiation, and practical decision-making skills.
Culture & Benefits
Full-time hybrid work in Toronto.
Work with a small, distributed team of strong engineers across multiple locations.
Culture emphasizing ownership, collaboration, accountability, diversity, grit, passion, and humility.
Accessibility accommodations are available throughout the recruitment process.
Equal employment opportunity is provided across legally protected characteristics.
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 →