Senior ML Engineer

Jobtailor; Deutschland; Remote; EUR 120.000 - 180.000; Vollzeit

Zusammenfassung

Jobtailor is seeking an experienced machine-learning engineer to own the recommendation engine, focusing on time-series forecasting, anomaly detection, and production-grade Python code. You will design scalable ML systems, optimize Kubernetes workloads, and maintain data-quality layers in production.

Collaboration with cross-functional teams will be essential to drive accuracy and safety metrics. The role emphasizes ownership of ML models, rigorous testing, and a proactive approach to capacity

Qualifikationen

• Master's degree or higher in a quantitative field (Computer Science, Machine Learning, Statistics, Applied Mathematics)
• 5+ years of software engineering experience
• At least 3 years building and operating machine learning or statistical systems in production
• Expert-level Python, including typed, tested, production-grade code
• Fluency in numpy or similar array-based numerical computing
• Hands-on experience with time-series analysis and forecasting, including seasonality, trend decomposition, anomaly detection, and classical statistical methods
• Experience testing ML systems rigorously, including regression testing against known-good baselines, behavioral validation, and numerical reproducibility
• Working knowledge of Kubernetes, including resource requests and limits, autoscaling behavior, OOM kills, and CPU throttling
• Comfort owning a production service, including queues, caches, retries, observability, and debugging customer-environment issues from logs and metrics
• Clear written and verbal communication
• Experience with Prophet or similar forecasting libraries is beneficial
• Prometheus/PromQL and experience working with metrics at scale is beneficial
• Cloud cost optimization, capacity planning, or infrastructure efficiency background is beneficial
• AWS (S3, Managed Prometheus) experience is beneficial
• Experience being the ML domain expert on a team of generalists is beneficial

Aufgaben

• Own the recommendation engine end to end, including model selection, algorithm design, preprocessing, and safety guardrails
• Design, evaluate, and productionize time-series forecasting and statistical models for right-sizing Kubernetes workloads across CPU, memory, GPU, and JVM heap
• Build and maintain the data-quality layer by detecting and filtering anomalies, load-test windows, startup spikes, and autoscaling artifacts from production telemetry
• Define and improve recommendation-quality measurement through regression testing, behavioral validation, and production accuracy and safety metrics
• Investigate and resolve recommendation-quality issues from customer environments by tracing data, preprocessing, and model behavior
• Serve as the team's machine learning authority and guide technical direction on ML questions and model-versus-heuristic tradeoffs
• Write production-grade Python for models and pipelines and share ownership of message consumption, metrics ingestion, and caching services
• Prototype and validate new optimization capabilities from research through gradual, feature-flagged rollout
• Stay current on time-series forecasting and resource optimization techniques and evaluate which are worth adopting

Kenntnisse

Machine Learning

Statistical Modeling

Time-Series Forecasting

Anomaly Detection

Python Programming

Regression Testing

Behavioral Validation

Numerical Computing

Kubernetes

Cloud Cost Optimization

Clear Communication

Problem-Solving

Ausbildung

Master's Degree in Quantitative Field

Tools

Prophet

Prometheus

PromQL

AWS

Metrics Ingestion

Jobbeschreibung

• Own the recommendation engine end to end, including model selection, algorithm design, preprocessing, and safety guardrails
• Design, evaluate, and productionize time-series forecasting and statistical models for right-sizing Kubernetes workloads across CPU, memory, GPU, and JVM heap
• Build and maintain the data-quality layer by detecting and filtering anomalies, load-test windows, startup spikes, and autoscaling artifacts from production telemetry
• Define and improve recommendation-quality measurement through regression testing, behavioral validation, and production accuracy and safety metrics
• Investigate and resolve recommendation-quality issues from customer environments by tracing data, preprocessing, and model behavior
• Serve as the team's machine learning authority and guide technical direction on ML questions and model-versus-heuristic tradeoffs
• Write production-grade Python for models and pipelines and share ownership of message consumption, metrics ingestion, and caching services
• Prototype and validate new optimization capabilities from research through gradual, feature-flagged rollout
• Stay current on time-series forecasting and resource optimization techniques and evaluate which are worth adopting

Requirements

• Master's degree or higher in a quantitative field (Computer Science, Machine Learning, Statistics, Applied Mathematics)
• 5+ years of software engineering experience
• At least 3 years building and operating machine learning or statistical systems in production
• Expert-level Python, including typed, tested, production-grade code
• Fluency in numpy or similar array-based numerical computing
• Hands-on experience with time-series analysis and forecasting, including seasonality, trend decomposition, anomaly detection, and classical statistical methods
• Experience testing ML systems rigorously, including regression testing against known-good baselines, behavioral validation, and numerical reproducibility
• Working knowledge of Kubernetes, including resource requests and limits, autoscaling behavior, OOM kills, and CPU throttling
• Comfort owning a production service, including queues, caches, retries, observability, and debugging customer-environment issues from logs and metrics
• Clear written and verbal communication
• Experience with Prophet or similar forecasting libraries is beneficial
• Prometheus/PromQL and experience working with metrics at scale is beneficial
• Cloud cost optimization, capacity planning, or infrastructure efficiency background is beneficial
• AWS (S3, Managed Prometheus) experience is beneficial
• Experience being the ML domain expert on a team of generalists is beneficial

Core Competencies

Demonstrates expertise in machine learning model development and deployment, with a strong focus on time-series forecasting, anomaly detection, and production-grade Python coding. Proven ability to own and optimize recommendation systems while ensuring data quality and operational efficiency.

Highest-signal resume keywords

• Machine Learning Expertise
• Production-Grade Python Development
• Time-Series Analysis and Forecasting
• Kubernetes Resource Management
• Data Quality Assurance

ATS Optimization Keywords

Hard Skills

• Machine Learning
• Statistical Modeling
• Time-Series Forecasting
• Anomaly Detection
• Python Programming
• Regression Testing
• Behavioral Validation
• Numerical Computing
• Kubernetes
• Cloud Cost Optimization

Soft Skills

• Clear Communication
• Problem-Solving

Certifications & Qualifications

• Master's Degree in Quantitative Field

Industry Keywords

• Recommendation Engine
• Data Quality Layer
• Resource Optimization
• Production Telemetry
• Capacity Planning

Tools & Technologies

• Prophet
• Prometheus
• PromQL
• AWS
• Metrics Ingestion