Bio

I work in the Lyft ML Platform team. We develop and maintain the Tier 0 Lyft ML Platform backend infrastructure that enable Machine Learning Models to schedule and dispatch rides efficiently. I am working on enabling scalable distributed Machine Learning on the Platform. I also enabled the Spark Notebooks on Kubernetes feature on the platform for ML Prototyping on large data and creating on-demand Spark K8s Cluster. I also developed Automated Model Training & Deployment, Model promotion & demotion workflows and Model Monitoring capabilities. I have worked with Spark, Kubernetes, AWS Sagemaker, Kubeflow and Seldon across various projects. Prior to that I worked on Machine Learning initiatives and projects. Designed, developed and deployed PySpark MLlib models on Spark clusters. Also performed data wrangling, cleaning and mining of Time Series data; analysing and identifying trends of storage metrics data; used statistical methodologies for outlier detection; devised custom strategies for missing values treatment etc. MS in Computer Science from the Texas A&M University. Seasoned Java & J2EE Senior Technical Lead. 6 years of USA work/study experience. 2 years as a Technical Architect on implementing BPM solutions in Java. 2 years of experience in developing and co-architecting multi-threaded Java application frameworks for a financial customer. 3+ years of Industry experience in Machine Learning software and platform engineer. Well versed with Agile methodologies. Worked in all phases of SDLC viz. Business & System Requirement Gathering, Effort Estimations and Task Planning, Architecting & Design, Component Development, Implementation, Performance Tuning etc. Skill Sets: Kubernetes, Spark, Machine Learning, Data Mining, NLP, Java, J2EE Programming Languages: Java 6,8(12+ years), Python(3 yrs) Machine Learning: scikit-learn, pandas, Keras, Tensorfloe, Pytorch, XGBoost, Spark Mllib etc. Big Data & Distributed: Spark, Kubernetes, Kubeflow, Hive, AWS Ecosystem, AWS SageMaker Java Frameworks: Spring 4x, Spring Boot, REST Messaging: Kafka (exposure) PyCharm, Eclipse, IntelliJ Idea, Maven, Git, GitHub, Jenkins NoSql Exposure: Redis, Neo4j | RDBMS Experience: Oracle 9i & 10g, IBM DB2 6.1, MySQL https://github.com/anindya-saha/Machine-Learning-with-Python https://github.com/anindya-saha/Data-Science-with-Spark Interested in engineering distributed Machine Learning systems. e-mail mail.anindya at gmail dot com