Machine Learning Engineer, Contact Center Solutions

We are seeking a highly skilled Machine Learning Engineer to design, test, and deploy predictive machine learning models—with a primary focus on time series forecasting and classification solutions—within the contact center. This role focuses on hands-on data science development, exploratory data analysis, feature engineering, and rigorous model testing, working closely with product managers and operations teams. You will help build AI-driven solutions across the contact lifecycle to predict volumes, classify customer intents, and drive meaningful performance and customer experience improvements. Additional experience in Generative AI (GenAI) and AI engineering is highly preferred to help build hybrid predictive and generative solutions. 

Key Responsibilities – Solution Development: 

• Develop, train, and deploy machine learning models (specifically time series and classification models) to support contact center optimization, volume forecasting, and quality automation. 

• Build and maintain robust ML pipelines for data prep, feature engineering, model training, testing, and monitoring. 

• Apply MLOps best practices including CI/CD, model versioning, concept/data drift detection, and performance monitoring. 

• Perform advanced exploratory data analysis (EDA) to identify trends, seasonality, and patterns in historical contact center data. 

• Build time series forecasting models (e.g., ARIMA, Prophet, LSTMs) to predict call volumes, handle times, and resource demands. 

• Design classification models (e.g., Random Forest, XGBoost, Logistic Regression) to categorize customer intent, sentiment, or escalation risks. 

• Iterate on model features and architecture to improve predictive accuracy, stability, and consistency. 

• Integrate predictive ML models with enterprise data sources and operational dashboards. 

Key Responsibilities – Model Evaluation & Quality Assurance: 

• Design rigorous evaluation methodologies including cross-validation, backtesting for time series, and hyperparameter tuning. 

• Create scoring metrics tailored to operational scenarios (e.g., RMSE and MAPE for forecasting; Precision, Recall, and F1-score for classification). 

• Run side-by-side model comparisons, feature importance analysis, and maintain dashboards for accuracy, latency, and business impact. 

• Test data pipelines and model outputs against compliance, risk, and privacy guidelines. 

Key Responsibilities – Technical Solutioning & Prototyping: 

• Build end-to-end prototypes using Python, SQL, and data orchestration frameworks. 

• Experience developing and deploying traditional ML and deep learning models (supervised and unsupervised) in production. 

• Skilled with predictive ML frameworks such as scikit-learn, XGBoost, LightGBM, TensorFlow, or PyTorch. 

• Familiarity with MLOps tools (MLflow, Kubeflow, Azure ML) to ensure seamless model lifecycle management. 

• Develop pipelines to extract, clean, and prepare structured metadata, tabular data, and call transcripts for ML consumption. 

• Partner with software and data engineering teams to hand off production-ready inference logic and monitoring artifacts. 

Required Skills & Qualifications: 

• Hands-on experience with custom ML model development, specifically targeting time series forecasting and classification problems. 

• Strong programming skills in Python and SQL (pandas, numpy, scikit-learn, statsmodels). 

• Deep understanding of statistical modeling, predictive analytics, and forecasting techniques. 

• Experience working with large operational datasets, tabular data, and conversational datasets. 

• Familiarity with cloud services and enterprise data platforms (e.g., Azure, Databricks). 

Preferred Skills: 

• Hands-on AI Engineering experience with LLMs, prompt design, and Generative AI evaluation. 

• Experience implementing Retrieval-Augmented Generation (RAG) systems with vector databases to supplement predictive models. 

• Understanding of modern NLP concepts including semantic similarity, embeddings, and text summarization. 

• Knowledge of responsible AI, safety evaluation, model fairness, and compliance testing. 

When you join our team: 

• We’ll empower you to learn and grow the career you want. 

• We’ll recognize and support you in a flexible environment where well-being and inclusion are more than just words. 

• As part of our global team, we’ll support you in shaping the future you want to see. 

#LI-Hybrid