Staff Machine Learning Engineer

Staff Machine Learning Engineer at Home Depot / THD in Atlanta, GA (remote); salary $120,000–$190,000 per year; minimum 3 years of experience; High School Diploma or GED.

Responsibilities

• Partner with cross functional teams including UX, engineering, and product management to design secure, reliable, and scalable ML solutions
• Ensure user stories are developer-ready, clear, and testable in collaboration with the Product Team
• Tune off the shelf software to meet evolving business needs
• Build dashboards, logging, alerts, and response workflows to detect and address issues proactively
• Engage in learning activities on modern software design, machine learning, and core development practices via communities of practice
• Regularly review external articles, tutorials, and videos to stay current with new technologies and best practices
• Attend conferences to evaluate and adopt new innovations when appropriate
• Analyze business trends and behavioral data to identify opportunities for improvement and new initiatives
• Lead evaluation, development, and recommendations of technology products and platforms to deliver cost effective solutions
• Research and design suitable infrastructure, networking, databases, security, and ML architectures for products
• Create and maintain monitoring and support tools
• Contribute to project planning and manage multiple initiatives
• Develop formal training programs
• Answer questions from other product or support teams
• Monitor tools and foster collaboration across product teams
• Provide production support for deployed software
• Track production service level objectives and product performance
• Periodically assess production performance and capacity across code, infrastructure, data, messaging, and model quality

Requirements

• Must be eighteen years of age or older
• Must be legally permitted to work in the United States

Minimum Qualifications

• High School Diploma or GED
• At least 3 years of relevant work experience

Preferred Qualifications

• 3 to 6 years of relevant work experience
• Proven experience designing, training, evaluating, and deploying ML models in production, including batch and real time inference
• Hands on ML lifecycle management experience covering feature engineering, model versioning, experimentation, validation, and monitoring for data drift and performance degradation
• Experience building and operating ML pipelines with cloud native services, data platforms, and CI/CD practices for reproducible deployments
• Solid understanding of applied statistics, model evaluation metrics, and tradeoffs among accuracy, interpretability, latency, and operational cost
• Experience with clustering, forecasting, anomaly detection, and neural networks
• Foundation in basic statistics and regression algorithms
• Exposure to advanced ML techniques such as NLP, CNNs, autoencoders, and embeddings
• Experience training ML models on very large datasets
• Proficiency with data analysis and ML tools like Jupyter, Pandas, SciPy, Scikit-learn, Gensim, TensorFlow, and PyTorch, and integrating them into scalable systems
• Experience with Google Cloud Platform and AI/ML components such as Vertex AI, BigQueryML, and AutoML
• Familiarity with data engineering practices and big data platforms like BigQuery and DataStore
• Proficiency in a modern scripting language, preferably Python
• Experience writing SQL queries against relational databases
• Experience with version control systems, preferably Git
• Experience in Linux or Unix environments
• Experience with CI/CD toolchains
• Experience with REST and well designed web services
• Experience designing production systems with High Availability, Disaster Recovery, performance, efficiency, and security considerations
• Experience with cloud computing platforms and automation patterns for ML services
• Familiarity with defensive coding patterns for high availability
• Experience with A/B testing and scalable REST based web services design
• Familiarity with advanced ML architectures such as GANs, GRU, LSTM, RNNs, CNNs, and style transfer

Technologies

• Python
• SQL
• Git
• Linux
• Unix
• Google Cloud Platform
• Vertex AI
• BigQuery
• BigQueryML
• AutoML
• Jupyter Notebooks
• Pandas
• SciPy
• Scikit-learn
• Gensim
• TensorFlow
• PyTorch
• REST
• CI/CD
• Datastore

Reporting and Team Structure

• Typically reports to Software Engineer Manager or Senior Software Engineer Manager
• 0 direct reports

Travel Requirements

• Typically requires overnight travel 5% to 20% of the time

Physical Requirements

• Most time spent sitting in a comfortable position, with occasional light movement or lifting

Working Conditions

• Indoor office environment with generally comfortable conditions; unpleasant conditions are infrequent