Machine Learning Engineer

Summary

Join Accesa, a leading technology company, and become a key player in a strategic initiative focused on developing predictive maintenance algorithms for a client's manufacturing operations. Lead the development of data pipelines, design and implement anomaly and failure detection models, and collaborate with cross-functional teams. You will ensure delivery excellence through explainable AI and robust MLOps practices. Mentor team members and guide them through the ML lifecycle. This role requires expertise in Python, data science, machine learning, and MLOps. The successful candidate will have experience with various algorithms and frameworks, including time-series models and explainable AI tools.

Requirements

• 4+ years of experience with Python and its data science ecosystem (Pandas, NumPy, Scikit-learn), fundamental for data manipulation and modeling
• Proficiency in advanced feature engineering techniques, including the transformation of raw sensor data (such as vibration or temperature readings) into meaningful features for machine learning models, with skills in handling missing values, creating time-windowed statistics (e.g., rolling averages), and applying frequency-domain analysis (e.g., FFTs)
• Hands-on experience with unsupervised anomaly detection algorithms, such as Isolation Forest and One-Class SVM, essential for learning normal machine behavior and detecting deviations when labeled failure data is not available
• Solid expertise in supervised machine learning models, including Random Forest and XGBoost for fault classification, along with practical experience in time-series networks (e.g., LSTM) for Remaining Useful Life (RUL) prediction
• Good understanding of explainable AI frameworks, such as LIME and SHAP, to ensure transparency and trust in model decisions for maintenance teams
• Experience with MLOps practices and tools, including MLflow or similar frameworks, to manage experiment tracking, model versioning, and ensure a reproducible and maintainable machine learning lifecycle

Responsibilities

• Lead technical delivery: Drive the development of pipelines for transforming raw sensor data using time-windowing, FFT, and domain-specific features. Ensure scalable, high-quality data processing aligned with best practices and reproducibility standards
• Shape architecture: Design and implement anomaly and failure detection models, both unsupervised (Isolation Forest, One-Class SVM) and supervised (XGBoost, Random Forest), ensuring robust and compliant architectures while staying current with relevant frameworks
• Collaborate across roles: Bridge data science, engineering, and domain teams to align on requirements and delivery plans. Support RUL forecasting with time-series models like LSTM, ensuring outputs are clear and actionable
• Ensure delivery excellence: Apply explainable AI tools (LIME, SHAP) and create diagnostic visualizations to build trust and transparency. Maintain strong experiment tracking, versioning, and deployment using MLflow for reliable production workflows
• Mentor and support: Guide the team through the ML lifecycle, secure deployments, and monitoring. Provide mentorship, support onboarding, and encourage technical growth and consistency

Benefits

• Enjoy our holistic benefits program that covers the four pillars that we believe come together to support our wellbeing, covering social, physical, emotional wellbeing, as well as work-life fusion
• Physical Wellbeing: Our wellbeing program includes medical benefits, gym support, and personalized fitness options for an active lifestyle, complemented by team events and the Healthy Habits Club
• Work-Life Fusion: In very dynamic industries such as IT, the line between our professional and personal lives can quickly become blurred. Having a one-size-fits-one approach gives us the flexibility to define the work-life dynamic that works for us
• Emotional Wellbeing: We believe that to maintain our overall health, we need to invest in our mental wellbeing just as much as we do in our physical health, social connections or in achieving work-life balance
• Social Wellbeing: As a growing community in a hybrid environment, we want to ensure we remain connected not just by the great work we do every day but through our passions and interests