# Sasi Nakka > Applied Data Scientist | Machine Learning, Deep Learning | Computer Vision, NLP | Delivered Production-Grade ML Pipelines at Scale | IEEE Conference Author Location: United States, United States Profile: https://flows.cv/sasinakka My career started in analytics, working with real operational and healthcare data where accuracy and accountability mattered. That experience taught me an early lesson: models are only valuable if people can trust and use them. Wanting to move beyond dashboards and analysis, I transitioned into machine learning to build systems that make decisions, not just reports. Over the years, I’ve worked across finance, healthcare, retail, and sports analytics, taking ownership of increasingly complex ML problems. I’ve built fraud detection and risk scoring models, developed large scale computer vision pipelines that process broadcast video, and designed production ML systems that support real business workflows. Each role pushed me closer to the intersection of modeling, engineering, and production. More recently, my work has focused on building reliable ML and GenAI systems that operate at scale. I care deeply about how models behave after deployment, including data quality, monitoring, performance drift, and system reliability. I enjoy working on problems where engineering discipline matters as much as model quality. What motivates me most is impact and ownership. I like being close to the system end to end, collaborating with engineers, researchers, and product teams to make sure what we build solves the right problem and holds up in real world conditions. I am now looking for opportunities where I can continue building production ML systems, particularly in computer vision and GenAI, on teams that value strong engineering, thoughtful design, and real world impact. ## Work Experience ### Data Scienctist Specialist @ Invisible Technologies Jan 2025 – Present | Palo Alto, CA Developed computer vision pipelines for sports analytics on broadcast video, enabling player tracking and event detection to extract performance metrics. Deployed a low-latency conversational search system over 500+ technical components using LangChain and FastAPI, achieving <150ms response times and 91% answer accuracy via LLM-as-judge evaluation. ### Machine Learning Engineer @ Goldman Sachs Jan 2024 – Jan 2025 | United States .Built end-to-end health records policy and fraud detection and risk-scoring ML systems using XGBoost, LightGBM, and time-series anomaly detection, reducing false positives by ~25%. Designed scalable batch and near–real-time inference pipelines processing millions of transactions daily, added SHAP-based explainability for compliance, and automated training and deployment with MLflow and CI/CD—driving a ~35% reduction in fraud losses during pilot rollout. ### Machine Learning Researcher @ University of North Carolina at Charlotte Jan 2024 – Jan 2024 | NC, USA • Developed autonomous underwater robots with high-resolution optical sensors, reducing inspection costs by 93% and enhancing defect detection reliability through improved data collection and real-time analysis capabilities. • Enhanced YOLOv5 model performance by applying Gaussian filtering and CLAHE, achieving 87% higher defect detection accuracy and optimizing CSPDarknet53 with FPN and PANet for 90.7% precision, 88.3% recall, and 12ms inference time. ### Python Coding Teacher @ University of North Carolina at Charlotte Jan 2023 – Jan 2024 | United States • Delivered engaging lessons on advanced ML concepts, including Random Forests, Transformers, and Gradient Boosted Machines, enabling students to build projects like predictive models and text summarization systems. • Mentored students on cutting-edge AI topics such as Generative AI and Recommendation Systems, incorporating real-world techniques like GPT, Collaborative Filtering, and Matrix Factorization to foster hands-on problem-solving skills. ### Graduate Teaching Assistant @ University of North Carolina at Charlotte Jan 2023 – Jan 2024 | Charlotte, North Carolina, United States • Conducted workshops for over 50 students, guiding them in implementing ML models such as Random Forests, ARIMA, and Transformers, resulting in a 30% improvement in their practical understanding and project outcomes. • Assisted in research projects by developing DL architectures like LSTMs and utilizing tools like SHAP and LIME, leading to a 20% increase in model interpretability and contributing to successful completion of two key forecasting studies. ### Data Scientist @ Samsung India Jan 2022 – Jan 2023 | Bangalore Harman International- project at Samsung, I built scalable data platforms using BigQuery, Trino, and Airflow, powering 500+ analytics workflows with GDPR compliance and real-time reliability. I developed anomaly detection and forecasting models using Python and XGBoost to improve data quality and operational insight. My work involved containerizing services with Docker and Kubernetes, and implementing CI/CD for robust, testable pipelines. I collaborated across engineering, data, and product teams to deploy ML-integrated systems that scaled across global retail use cases. ### Data Analyst @ UnitedHealth Group Jan 2020 – Jan 2022 | Hyderabad Analyzed large-scale clinical and operational healthcare datasets to uncover insights on patient outcomes, treatment effectiveness, and resource utilization. Built predictive models to reduce readmissions by ~12% and developed interactive Power BI dashboards for real-time KPI tracking. Designed optimized data models and automated pipelines using Azure Data Factory, improving reporting efficiency by ~40%. Ensured data quality, applied statistical analysis for decision-making, and maintained HIPAA compliance while collaborating with stakeholders to drive actionable improvements. ## Education ### Master's degree in Computer Science University of North Carolina at Charlotte ## Contact & Social - LinkedIn: https://linkedin.com/in/sasi-pretham --- Source: https://flows.cv/sasinakka JSON Resume: https://flows.cv/sasinakka/resume.json Last updated: 2026-04-17