About

Kartikeya Sharma is a Senior Machine Learning Engineer with over 4 years of experience in building ML pipelines and automating ML systems. Currently working at Mad Street Den, he is responsible for designing and developing scalable orchestration solutions using Airflow pools and Databricks instance pools, resulting in a reduction of compute costs by more than 2X. Kartikeya is a quick and passionate learner with experience in a wide range of Open Source software and tools. He has a Master's degree in Computer Science from the National Institute of Technology Hamirpur, where he also completed his Bachelor's degree in Computer Science. In his previous role as a Machine Learning Engineer at Mad Street Den, Kartikeya designed and built a python library to promote reusable, structured feature extraction and model development code. He also built an end-to-end Alternating Least Squares + Locality Sensitive Hashing based recommendation system using PySpark, MlFlow, Redis to produce recommendation output at item to item level and did performance tuning of the same. He used Structure Streaming and Delta Lake to build an ML framework to find trending products based on user interactions flowing through Kafka. Kartikeya's experience also includes working as a Student Developer at Metabrainz Foundation, where he worked on the project “A way to associate listens with MBIDs”. He wrote scripts to execute series of SQL queries to perform associations, tuned SQL queries to increase the efficiency of the queries to perform associations in minutes as compared to hours, and utilized RabbitMQ to push the data across systems and wrote API to fetch the associations for further analysis. Kartikeya's tech stack includes ML, Python, SQL, Search, Databricks, AI, Recommendation system, Java, Spark, Scikit, Deep Learning, Apache Airflow, Kubernetes, Tensorflow, Redis, Kafka, Keras, Seaborn, RabbitMQ, Docker, Pandas, and Jenkins. He is currently looking for a role in the field of ML Engineering where he'll be working on making ML systems more scalable and ML workflows more efficient.