Machine Learning Engineer

Responsibilities

• Optimize model inference for real-time recommendations.
• Containerize ML models using Docker/Kubernetes.
• Build REST APIs for the recommendation engine.
• Monitor model drift and retraining pipelines.
• Productionize machine learning models for fashion and fit recommendations, ensuring low-latency inference and high scalability.
• Deploy recommendation models using REST/gRPC APIs for real-time and batch inference.
• Optimize models for performance, memory usage, and response time in high-traffic environments
• Implement hybrid recommendation pipelines combining collaborative filtering, content-based filtering, and contextual signals (season, region, trends).
• Integrate stylist-curated rules and human-in-the-loop feedback into ML-driven recommendations.
• Support personalization based on body type, height, skin tone, ethnicity, and user style profiles.
• Build and maintain end-to-end MLOps pipelines including training, validation, deployment, monitoring, and retraining.
• Containerize ML services using Docker and orchestrate deployments with Kubernetes.
• Implement CI/CD pipelines for ML models and inference services.
• Monitor model performance, drift, bias, and recommendation quality in production.
• Design automated retraining workflows based on data freshness and performance metrics.
• Collaborate with Data Scientists to tune ranking, diversity, and relevance metrics.

Qualifications:

• Solid understanding of MLOps practices, including MLflow, model registries, and feature stores.
• TensorFlow Serving, FastAPI / REST API.
• MLOps and CI/CD pipelines.
• Experience with scalable deployment architectures.
• Strong proficiency in Python and ML frameworks such as TensorFlow, PyTorch, or Scikit-learn.
• Hands-on experience with recommendation systems (collaborative filtering, embeddings, ranking models).
• Experience with Docker, Kubernetes, and cloud platforms (AWS, GCP, or Azure).
• Knowledge of data storage systems (SQL/NoSQL) and caching mechanisms (Redis, Memcached).