Senior ML Engineer - Email Security (remote work)

Cloudlinux

1d • Remote

About The Position

CloudLinux is a global, remote-first company that develops Linux infrastructure and security products. Its Imunify Email product protects hosting servers against spam, phishing, and other email-based threats, filtering mail on about 5,000 hosting servers. The existing filter uses rspamd with rules and an in-house scoring model. CloudLinux is replacing it with a self-trained transformer designed to run on customers’ CPUs in under 100 MB.

The Senior ML Engineer will work alongside the engineer currently responsible for the spam-filtering pipeline and the new machine-learning model. Together, they will develop, improve, and roll out the company’s email security technology in production.

The first-six-month expectations are: by month 1, independently ship a rule-model release; by month 3, merge a first part of the new engine and have it running on staging; and by month 6, release a model while the principal engineer is away.

Requirements

• At least 5 years of experience shipping detection or classification systems where false positives have a cost, such as anti-spam, anti-phishing, anti-malware, fraud, or abuse systems.
• Experience personally taking at least one ML classifier to production, including corpus construction, threshold selection, and error analysis.
• Hands-on transformer training in PyTorch, including tokenizers, masked-language pre-training, fine-tuning, ONNX export, and CPU inference measurement.
• Experience using Linux, shell, and Python on shared servers and a shared GPU.
• Daily use of AI coding agents and tools.
• English proficiency at upper-intermediate (B2) level or higher, with particularly strong written communication skills for technical documentation, specifications, and code reviews.

Nice To Haves

• Knowledge of email internals, including SMTP, MIME, transfer encodings, SPF, DKIM, and DMARC, and how Exim, Postfix, and Dovecot handle mail sent to a filter.
• Experience creating embedded models.
• Go or Rust experience for systems code such as parsers, streaming, memory budgets, and concurrency.
• Knowledge of rspamd or SpamAssassin internals, including rules, composites, Lua plugins, and mass-check scoring.
• Experience with multi-million-sample corpora, labeling pipelines, or annotator tooling.
• Experience building small models for constrained hardware, including quantization, distillation, or latency budgets.
• Experience with LLM-based labelers or validators for scaling annotation.
• Experience with hosting panels such as cPanel, Plesk, or DirectAdmin.

Responsibilities

• Train, evaluate, and release spam-detection models, including building the corpus, selecting thresholds, reviewing precision and recall, and deciding whether to ship or retrain.
• Build the production side of the new engine in Go, including the inference service, mail-filter integration, tokenizer, and streaming message parser.
• Improve detection quality end to end by investigating customer reports, making rule or corpus changes, and retraining models while weighing false-positive costs against detection.
• Maintain corpus tooling and training infrastructure.
• Review and approve classifier, rule, and model changes so releases do not depend on one person.
• Respond to partner engineers’ questions about why messages received particular scores.
• Write specifications, handbooks, and post-mortems to transfer team knowledge.

Benefits

• Professional development focus and an education budget.
• Fully remote work from any location worldwide with flexible working hours.
• 24 paid vacation days per year, 10 days of national holidays, and unlimited sick leave.
• Compensation for private medical insurance.
• Co-working and gym/sports reimbursement.
• Opportunity to receive a reward for the most innovative idea the company can patent.
• Interesting and challenging projects.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed