ML engineer in email security

CloudLinux Inc.; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Fully remote work

Flexible working hours

Paid vacation and holidays

Private medical insurance

Co-working and gym reimbursement

Education budget

Innovation reward

Job summary

CloudLinux Inc. ищет старшего инженера по машинному обучению для разработки и развёртывания систем детекции спама и угроз в почте. Вы будете работать рядом с существующей командой и отвечать за обучение, оценку и внедрение новых моделей в продакшн.

Требуется опыт вывода ML-моделей в продакшн, работа с трансформерами в PyTorch, владение Python и Linux. Вакансия удаленная с гибким графиком, с международной командой и возможностями развития.

Qualifications

• 5+ лет опыта вывода детекции или классификационных систем, где ложные срабатывания стоят цены
• У вас был как минимум один ML-классификатор в продакшне: построение корпуса, порог, анализ ошибок
• Опыт обучения трансформеров в PyTorch: токенизаторы, pre-training, fine-tuning, ONNX, CPU-inference

Responsibilities

• Обучение, оценка и релиз моделей детекции спама
• Разработка продакшн-стороны нового движка на Go: сервис инференса, интеграция фильтра, токенизатор
• Поддержка качества и исправление ошибок, анализ ложных срабатываний
• Ревью изменений моделей и правил, SOP и постмортемы
• Документация и инструкции для команды

Skills

5+ лет опыта вывода ML-моделей

Опыт вывода классификаторов

Обучение трансформеров в PyTorch

Python

Linux

Go/Rust для системного кода

Английский B2+

Tools

PyTorch

Git

Shell/Linux

Job description

Описание

One of these solutions is Imunify Email, an email security product that protects hosting servers against spam, phishing, and other email-based threats. We are looking for a Senior Machine Learning Engineer to join our team and work alongside the engineer currently responsible for both the existing spam-filtering pipeline and the new ML model. Together, you will drive the development, improvement, and production rollout of our email security technology.

Задачи

Train, evaluate, and release spam-detection models: build the corpus, pick the threshold, read the precision/recall report, decide ship or retrain Build the production side of the new engine in Go: the inference service, the mail-filter integration, the tokenizer, the streaming message parser Fix detection quality end to end, from a customer's "this phishing got through" to a rule, a corpus fix, or a retrain, with the false-positive cost weighed against the catch Keep the corpus tooling and training infrastructure running Review and approve classifier, rule, and model changes, so no release waits on one person Answer partner engineers who ask why a message scored the way it did Write specs, handbooks, and post-mortems. That is how this team transfers knowledge

Требования

• 5+ years of shipping detection or classification systems where false positives have a cost you had to defend: anti-spam, anti-phishing, anti-malware, fraud, abuse
• You have taken at least one ML classifier to production yourself: corpus construction, threshold selection, error analysis
• Hands-on transformer training in PyTorch: tokenizers, masked-language pre-training, fine-tuning, ONNX export, CPU inference measurement
• Linux, shell, and Python on shared servers and a shared GPU
• Daily usage of AI coding agents and tools
• English at upper-Intermediate (B2) level or higher, with particularly strong written communication skills for technical documentation, specifications, and code reviews. Your specs and merge-request descriptions count as much as your code
• Будет плюсом: Email internals: SMTP, MIME, transfer encodings, SPF / DKIM / DMARC, how Exim, Postfix, and Dovecot handle mail to a filter; Experience in creating embedded models; Go or Rust for systems code: parsers, streaming, memory budgets, concurrency; rspamd or SpamAssassin internals: rules, composites, Lua plugins, mass-check scoring; Multi-million-sample corpora, labelling pipelines, annotator tooling; Small models for constrained hardware: quantization, distillation, latency budgets; LLM-based labelers or validators for scaling annotation; Hosting panels: cPanel, Plesk, DirectAdmin

Условия

• A focus on professional development
• Interesting and challenging projects
• Fully remote work with flexible working hours, that allows you to schedule your day and work from any location worldwide
• Paid 24 days of vacation per year, 10 days of national holidays, and unlimited sick leaves
• Compensation for private medical insurance
• Co-working and gym/sports reimbursement
• Budget for education
• The opportunity to receive a reward for the most innovative idea that the company can patent