Назад
Company hidden
2 дня назад

Lead ML Systems Engineer (Productionization & Inference Architecture)

Формат работы
hybrid
Тип работы
fulltime
Грейд
lead
Английский
b2
Страна
Poland
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Lead ML Systems Engineer (Productionization & Inference Architecture) (Machine Learning/AdTech): Define and build productionization frameworks that move machine-learning models from Databricks experimentation into scalable real-time advertising systems with an accent on feature pipelines, model packaging, inference architecture, and cost-efficient execution. Focus on reducing duplicated computation, integrating CPU/GPU inference with the rAVE runtime, and establishing strict contracts across ML Platform and inference-runtime systems.

Location: Warsaw, Poland; hybrid and flexible work environment

Company

hirify.global is a mobile growth platform connecting advertisers, app developers, device partners, carriers, OEMs, publishers, and consumers through intelligent mobile experiences.

What you will do

  • Define the technical direction for reusable ML productionization frameworks covering dependencies, feature processing, execution environments, validation, deployment, packaging, versioning, and reproducibility.
  • Connect Databricks-based experimentation with production execution through training artifacts, featurization pipelines, feature consistency, and dependency management.
  • Optimize feature extraction, transformation, joins, curation, model execution, and computational efficiency across Python, Polars, Ray, Spark, ONNX, and CPU/GPU environments.
  • Design scalable inference approaches that reduce duplicated computation through shared features and reusable intermediate representations.
  • Define payload contracts and integration patterns for models running on rAVE, collaborating with core runtime engineers on performance bottlenecks and model-to-runtime integration.
  • Lead platform evaluation, technical roadmaps, engineering standards, and cross-functional alignment across Data Science, ML Platform, feature infrastructure, and inference-runtime teams.

Requirements

  • Strong software engineering background with deep Python expertise and experience designing reusable frameworks or platforms for production ML or data-processing workloads.
  • Experience designing and operating production ML systems, including model lifecycle management, packaging, validation, deployment, and monitoring.
  • Strong understanding of profiling, memory management, parallelism, data-processing overhead, and resource utilization.
  • Experience making architectural trade-offs across data-processing systems, data access patterns, execution environments, distributed processing, model-serving systems, and cloud infrastructure.
  • Ability to balance model complexity, inference throughput, latency requirements, infrastructure utilization, and total cost of ownership.
  • Experience designing systems that integrate multiple models, shared features, or common computational components.
  • Familiarity with Rust or experience working across language boundaries, including establishing strict contracts for integration with a Rust-based inference runtime.
  • Experience with cloud infrastructure, automated delivery pipelines, production observability, and reliability engineering.
  • Strong technical leadership and the ability to establish architecture, influence cross-functional teams, and turn ambiguous problems into an executable engineering roadmap.
  • Experience with Python data-processing tools including NumPy, pandas, and PyArrow; MLflow; Databricks; Spark/PySpark; production data-processing pipelines; cloud infrastructure; containerization; CI/CD; Airflow; model-serving interfaces; performance profiling; and observability.

Nice to have

  • Rust and integration with high-performance inference runtimes.
  • ONNX, ONNX Runtime, nvForest, GPU training with PyTorch, GPU inference, or neural-network serving.
  • SQL and experience with OLAP or OLTP systems.
  • Analytical and transactional data architectures, online feature stores, real-time feature pipelines, and distributed data-serving architectures.
  • Bigtable, Aerospike, or similar low-latency data stores.
  • Advertising technology, real-time bidding, or other high-throughput, latency-sensitive systems.
  • Infrastructure-cost optimization for compute-intensive or large-scale ML workloads.

Culture & Benefits

  • Fast-moving, collaborative environment with ownership and opportunities to challenge convention.
  • Products and experiences used by millions of people worldwide.
  • Competitive compensation, equity awards, and a comprehensive benefits package.
  • Hybrid and flexible work environment.
  • Inclusive and diverse workplace with equal-opportunity employment practices.

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 →