Detection Engineer
Se anima a todos los posibles solicitantes a que se desplacen y lean la descripción completa del puesto antes de presentar su candidatura.

Bring every AI agent out of the box from google and crowdstrike to live.

Join a global enterprise's cyber defense function as the engineer who brings machine learning into the detection workflow. The mission: move detection beyond static rules into predictive, model-driven threat identification — surfacing patterns, anomalies, and behavioral signals across EDR and SIEM telemetry. You'll partner closely with detection engineers, threat hunters, and cyber threat intelligence to catch what rule-based systems miss.

What you'll do

-

- Design, train, and deploy machine learning models for threat detection, with a focus on anomaly detection, behavioral analytics, and user/entity behavior analysis across endpoint and SIEM data sources.

- Build and maintain AI-driven detection pipelines capable of continuous learning as new threats emerge.

- Work with Detection Engineers to turn model outputs into explainable, actionable detection logic that SOC analysts can triage with confidence.

- Own feature engineering and training data curation across endpoint and SIEM telemetry, with attention to data quality, labeling accuracy, and statistical relevance.

- Identify and mitigate AI-specific risks, including model drift, biased training data, adversarial inputs, and automation over-reliance.

- Stay ahead of the evolving adversarial AI landscape — AI-generated phishing, evasive malware, deepfake-enabled social engineering — and build countermeasures into the detection stack.

- Bring an MLOps discipline to the role: version control for models,



production performance monitoring, and ongoing evaluation of precision, recall, and false-positive rates against team KPIs.

What you'll bring

-

- 3+ years applying machine learning to cybersecurity, fraud detection, or large-scale anomaly detection challenges.

- Strong Python fundamentals and hands‑on experience with ML frameworks such as scikit‑learn, PyTorch, TensorFlow, or XGBoost, spanning both classical and deep learning methods.

- Practical familiarity with endpoint detection and response tools, SIEM platforms, and an understanding of how detection pipelines consume model output.

- Solid grounding in feature engineering, model evaluation, and handling class imbalance.

- Exposure to MLOps practices: model versioning, monitoring, and retraining workflows, using tools like MLflow, Vertex AI, or similar.

- Awareness of adversarial ML risks (model poisoning, evasion techniques, prompt injection) and mitigation approaches in live environments.

What's on offer

-

- Hybrid working model balancing in‑office collaboration and remote flexibility, including the option to work abroad for part of the year.

- Performance‑based rewards: bonus scheme, pension contribution, employee share program, and additional discounts (varies by location).

- Ongoing career development, learning and training budget.

- Versátil work arrangements plus health, wellbeing, and family‑related benefits, including support for parental leave and returning from career breaks.

- "You run it - you build it" mindset. xqbhyrx Take ownership, bring your ideas, improve security inside the company, tackle new challenges and grow in your career inside the company.

#J-18808-Ljbffr

📌 Detection Engineer (Madrid)
🏢 Montash
📍 Madrid