Senior ML Engineer - Email Security

About the role

A partner company, acting on behalf of the hiring employer, is recruiting a Senior ML Engineer for a fully remote position in Estonia. The engineer helps develop and deploy machine learning technology that protects email infrastructure against spam, phishing and other cyber threats, on a production solution that already filters email across about 5,000 hosting servers. The role combines transformer model training with systems engineering to build lightweight, efficient inference running on customer CPUs.

Key responsibilities

• Train, evaluate and release spam-detection models, including building training corpora, choosing decision thresholds and analysing precision and recall.
• Develop the production components of a new email-filtering engine in Go, including the inference service, mail-filter integrations, tokenization and streaming message parsing.
• Investigate customer-reported spam and phishing incidents, trace detection failures and fix them through rules, dataset improvements or model retraining.
• Balance detection rates against false positives so legitimate messages are not blocked.
• Maintain corpus management tools and training infrastructure, and review and approve classifier, rule and model changes.
• Help partner engineers understand classification outcomes and write technical specifications, handbooks, merge-request descriptions and post-mortems.
• Progress toward milestones, including shipping a rule-model release independently in the first month, delivering a component of the new engine to staging by month three and supporting a model release independently by month six.

Required profile

• At least five years of experience delivering detection or classification systems where false positives matter, such as anti-spam, anti-phishing, anti-malware, fraud prevention or abuse detection.
• Experience taking at least one machine learning classifier into production, including corpus construction, threshold selection, error analysis and release decisions.
• Hands-on experience training transformers with PyTorch, including tokenizers, masked-language pre-training, fine-tuning, ONNX export and CPU inference performance measurement.
• Strong practical knowledge of Linux, shell scripting and Python, and regular use of AI coding agents.
• English at B2 level or higher, with strong written communication for documentation and code reviews.

Required skills

• PyTorch, ONNX, Linux, shell scripting, Python
• Nice to have: SMTP, MIME, SPF, DKIM, DMARC, Exim, Postfix, Dovecot; Go or Rust; rspamd or SpamAssassin internals; quantization, distillation and model optimisation; cPanel, Plesk or DirectAdmin

What we offer

• Fully remote work with flexible hours
• 24 days of paid vacation and 10 public holidays
• Unlimited sick leave and financial compensation toward private medical insurance
• Reimbursement for co-working spaces and gym or sports activities
• Education budget and innovation rewards for patentable ideas