I’m a Machine Learning Engineer with 5+ years of experience designing, training, and deploying production-scale ML systems across speech processing, real-time audio intelligence, and large-scale data platforms. I specialize in taking models from research to production, building reliable pipelines that operate on millions of records with strong performance, scalability, and evaluation guarantees.
I’ve worked extensively on uplift modeling, time-series feature engineering, and gradient-boosted models, building data-driven decision systems supported by statistically sound A/B testing frameworks and KPI monitoring. My work has focused on turning business objectives into measurable ML outcomes, optimizing targeting strategies, and improving ROI through model-driven experimentation.
I have a strong background in automatic speech recognition (ASR) and self-supervised learning, where I led initiatives in real-time sound event detection and developed multilingual speech-to-text models supporting multiple languages. I’m experienced in balancing accuracy, latency, and scalability in real-world production environments.
I also have hands-on experience deploying neural networks across CPU, GPU, and embedded platforms, using tools such as PyTorch, ONNX and CI/CD pipelines. Earlier in my career, I built object detection and classification systems and data collection pipelines, while developing strong communication, teamwork, and technical leadership skills.More...