Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
88
Хорошая вакансия
развернуть
Чётко очерченная senior-позиция в MLOps в продуктовой SaaS-компании даёт серьёзную ответственность за ML-системы в продакшене, но требование иметь право на работу в Румынии или на Мальте сужает круг доступных вариантов.
Ограничение по локации
Современный стек
Понятная зона ответственности
AI-продукт
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior AI/ML Engineer (MLOps): Productionizing, deploying, and optimizing machine learning systems for Implio, an AI-driven content moderation platform, with an accent on inference performance, reliability, and scalable operations. Focus on building training and retraining pipelines, optimizing ONNX/TensorRT inference, and implementing monitoring, CI/CD, and safe production rollouts.
Location: Fully remote; must be based in and have the right to work in Romania or Malta. B2B contracts are also available elsewhere in the EU.
Company
hirify.global delivers Trust & Safety solutions and Implio, a SaaS moderation platform combining AI, human moderation workflows, and analytics for online marketplaces worldwide.
What you will do
Own the production lifecycle of ML systems, including training, packaging, deployment, monitoring, controlled rollouts, and validation.
Design and improve training and retraining pipelines covering data ingestion, labeling and QA loops, feature generation, experiment tracking, and reproducibility.
Build high-performance inference services and deployment patterns, optimizing latency, throughput, memory use, GPU/CPU utilization, and cost with ONNX/TensorRT, quantization, and batching.
Partner with DevOps and SRE on scaling, reliability, observability, alerting, incident readiness, and operational excellence.
Own model versioning, CI/CD, release workflows, data and model monitoring, drift detection, and continuous feedback loops.
Communicate technical results and trade-offs to stakeholders and align model quality with evolving data and business needs.
Requirements
Master’s degree, PhD, or equivalent experience in Computer Science, Engineering, Data Science, or a related field, with strong foundations in mathematics, statistics, and machine learning.
6+ years of experience across ML engineering and MLOps or production ML, including a proven track record delivering high-impact systems in production.
Expertise deploying models to production, including scalable serving patterns, model packaging, inference optimization, observability, and safe rollout strategies.
Strong experience optimizing model performance and efficiency through latency and throughput tuning, batching, quantization, ONNX/TensorRT, GPU/CPU optimization, memory tuning, and cost tuning.
Strong Python proficiency and hands-on experience with PyTorch, scikit-learn, ONNX, and TensorRT.
Strong understanding of CI/CD for ML, including GitLab CI, containerization with Docker, and reproducible workflows.
Experience with monitoring and reliability practices, including metrics, logging, tracing, model and data drift, alerting, SLOs, and incident response.
Must be based in and have the right to work in Romania or Malta.
Nice to have
Kubernetes, AWS, FastAPI or similar Python serving frameworks, SageMaker, service meshes, feature stores, or model registries.
Culture & Benefits
100% remote work.
Full-time employment or B2B contract for candidates based in Romania or Malta; B2B contract for candidates elsewhere in the EU.
Collaborative work with Machine Learning Engineers, DevOps, and Developers.
Culture focused on execution, mutual support, professional growth, learning, knowledge sharing, and teamwork.
Applicants from all backgrounds are welcome.
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 →