У роли чёткий senior-фокус на ML- и data-инфраструктуре в production, с заметной ответственностью и подробно описанными задачами; крипторынок при этом добавляет отраслевой волатильности.
Волатильная отрасль
Понятная зона ответственности
Современные технологии
Поддержка развития
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Sr. Software Engineer, Machine Learning & Data Infrastructure (Machine Learning/Data Infrastructure): Building and operating ML infrastructure, production model-serving systems, and offline and online data pipelines for risk and fraud prevention with an accent on inference performance, distributed data processing, and reliable model lifecycle management. Focus on optimizing latency, throughput, resource utilization, feature correctness, deployment observability, and rollback across cloud platforms and regions.
Location: San Jose, California, United States; hybrid role
Salary: $178,888–$268,333 per year, plus potential performance bonus, long-term incentives, and benefits.
Company
OKX is a crypto exchange and developer of the OKX Wallet, providing access to crypto trading and decentralized applications.
What you will do
Improve model inference latency, throughput, resource utilization, and cost while preserving model quality.
Build and maintain model packaging, versioning, deployment, serving, monitoring, and rollback infrastructure across cloud platforms and regions.
Develop and optimize Databricks and Apache Spark offline data pipelines, including data modeling, partitioning, joins, shuffles, skew, incremental processing, and workload cost.
Build offline and online feature pipelines and reliable feature services with point-in-time correctness, freshness, lineage, reproducible backfills, and consistent feature definitions.
Support risk models and decision systems through data integrations, operational ownership, issue resolution, and collaboration with ML, data engineering, cloud infrastructure, security, and product teams.
Contribute to technical discussions, code reviews, knowledge sharing, and maintainable production systems.
Requirements
Experience building and operating distributed systems, ML infrastructure, or data platforms, with ownership of meaningful production components.
Hands-on experience improving production model performance, including latency, throughput, resource utilization, or cost.
Strong experience with Databricks and Spark or comparable offline data platforms, including execution plans, distributed query optimization, storage layouts, data correctness, and workload cost management.
Experience with the model lifecycle, including training and serving integration, validation, deployment, observability, and rollback.
Strong Python and SQL skills, plus proficiency in at least one backend or systems language such as Java, Scala, Go, or C++.
Ability to work independently through loosely defined problems, make sound implementation decisions, and deliver maintainable systems with limited guidance.
Nice to have
Experience with SageMaker, Alibaba Cloud PAI/EAS, or comparable ML platforms.
Inference optimization using ONNX Runtime, TensorRT, or Triton.
Experience with Delta Lake, MLflow, feature stores, Kafka, Flink, or low-latency data stores.
Experience with fraud detection or financial risk systems.
Fluency in Mandarin.
Culture & Benefits
Competitive total compensation with potential performance bonus and long-term incentives.
Learning and development programs.
Team-building programs and company events.
Wellness and meal allowances.
Comprehensive healthcare schemes for employees and dependants.
Equal employment opportunity workplace.
Hiring process
Apply through the OKX internal or external careers site.
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 →