Hire Jyoshna - Machine Learning Engineer

* Worked on applied machine learning and data science problems focused on ranking, personalization, and experimentation in production systems. * Developed and evaluated ranking and recommendation models serving 500K+ daily users, using offline metrics and A/B testing to measure impact on engagement and conversion * Designed experiments and partnered with product teams to define success metrics and prioritize model improvements * Built scalable ML pipelines and low-latency inference systems using PyTorch and TensorFlow with high reliability * Analyzed tradeoffs between accuracy, latency, and cost to optimize model performance in production * Collaborated cross-functionally with data science, engineering, and product teams to deliver ML-driven features end to end * Contributed to code reviews, system design discussions, and best practices for production-quality ML systems

* Worked on applied machine learning and data science problems focused on personalization, experimentation, and NLP in production-scale systems. * Developed and evaluated personalized recommendation models to improve click-through rate and conversion using offline metrics and experiment results * Analyzed user behavior and model performance to identify opportunities for personalization improvements * Built NLP pipelines using transformer-based models (BERT, DistilBERT) for large-scale document classification * Designed features and trained models using PyTorch and scikit-learn with a focus on robustness and generalization * Partnered with data scientists and engineers to deploy, monitor, and iterate on ML models in production environments * Participated in code reviews and design discussions to ensure high-quality, maintainable ML code

* Worked on applied machine learning and data science problems focused on ranking, forecasting, and large-scale predictive systems. * Built and evaluated ranking and demand forecasting models using TensorFlow and Spark ML to support decision-making for 500+ dealerships * Designed experiments and performed statistical analysis to improve predictive maintenance and forecasting accuracy * Developed and deployed scalable ML pipelines handling millions of daily predictions with monitoring and automated retraining * Implemented search and ranking algorithms over large telemetry datasets (80TB+) using distributed computing * Analyzed model performance and system tradeoffs to improve reliability, latency, and scalability * Mentored junior engineers on ML best practices, system design, and code quality