MLOps & Anomaly Detection Engineer

চাকরির বিবরণ

You will operationalise machine learning models and build anomaly detection systems monitoring real-world metrics — from CPU utilisation spikes (> 90% triggering automated alerts) to data drift signals. You will own the full ML lifecycle from training through production. WorkSprout is a deep-tech engineering and design partner across twelve practice areas — TinyML & Edge AI, Custom AI Development, AI Automation & Agents, Data Engineering & Collection, IoT Solutions, Hardware Prototyping, Robotics & Automation, 3D Design & Modeling, Software Development, Growth & DevOps, Branding & Creative Design, and Startup & Product Launch. We deliver systems that work in production, not just in demos. Office hours 09:00 – 18:00 BST, Monday to Friday; hybrid in Dhaka, Bangladesh. Applications are reviewed on a rolling basis. To apply, email careers@worksprout.us with the subject "MLOps & Anomaly Detection Engineer".

দায়িত্ব

• Build and maintain ML pipelines using MLflow, Kubeflow, or DVC
• Implement statistical and deep learning anomaly detection algorithms (Isolation Forest, LSTM, ARIMA)
• Create real-time alerting systems for infrastructure metrics including CPU, memory, and I/O thresholds
• Automate model retraining, versioning, and blue/green deployment workflows
• Set up feature stores and model registries for full reproducibility
• Collaborate with SRE teams to route ML alerts into incident management workflows

যোগ্যতা

• Experience with MLflow, DVC, or Kubeflow for experiment tracking and model registry
• Knowledge of anomaly detection techniques (Isolation Forest, LSTM, ARIMA, Prophet)
• Proficiency in Docker, Kubernetes, and CI/CD pipelines (GitHub Actions, Jenkins)
• Python with scikit-learn, PyTorch, or TensorFlow
• Strong grasp of time-series analysis and statistical process control
• Nice to have: Experience with Apache Kafka or Flink for streaming anomaly detection
• Nice to have: Familiarity with AWS SageMaker or GCP Vertex AI managed ML services
• Nice to have: Knowledge of A/B testing frameworks for model rollout comparison

সুবিধা

• Own end-to-end MLOps and monitoring infrastructure
• Competitive salary benchmarked to international rates
• Flexible hybrid work arrangement
• Access to cloud compute for model training at scale
• Opportunity to publish findings on anomaly detection in production systems