Sourabh Mundhra

AI Researcher

Bengaluru, Karnataka, India16 yrs 4 mos experience
Most Likely To SwitchHighly Stable

Key Highlights

  • Expert in building and productionizing machine learning models.
  • Proven track record in optimizing data pipelines.
  • Strong experience in developing scalable data solutions.
Stackforce AI infers this person is a SaaS-focused data engineering and machine learning expert.

Contact

Skills

Core Skills

Machine LearningData EngineeringSoftware Development

Other Skills

ALSAgile MethodologiesAkkaAlgorithmsApache SparkBoosted TreesCSSCore JavaData MungingData StructuresData VisualizationData WarehousingDistributed SystemsETLFraud Detection

About

Experienced Manager with a demonstrated history of building data pipelines, training and experimenting with machine learning algorithms and productionizing them.

Experience

16 yrs 4 mos
Total Experience
5 yrs 5 mos
Average Tenure
7 yrs 11 mos
Current Experience

Adobe

Senior Manager ML

Jul 2018Present · 7 yrs 11 mos · Bangalore

Capillary technologies

Tech Lead

Oct 2012Feb 2018 · 5 yrs 4 mos · Bengaluru Area, India

  • > Was the first member of the ml team at Capillary; working on predicting propensity of customer response to a campaign and product recommendation.This involved defining and computing features at scale in a multi-tenant system with lot of unclean custom data ; defining evaluation metrics to suit the business needs; training and evaluating ml models and serving the results. Worked end to end on all pieces of ml system.
  • > Came up with plethora of ideas to augment the Campaign Management System with ml based solutions. From tech stack perspective data munging/ml was in Scala/Spark and serving on akka; ml experimentation included work on logistic regression, boosted trees , random forest, xgboost , word2vec , ALS etc.
  • > Worked on POC which demonstrated multi-fold improvements in the existing ETL pipelines.
  • > Experimented on detecting fraud user engagement(GMM) and clustering(K-means) of the org-workloads in multi-tenant system for resource planning.
  • > Optimized the scheduling of query graph being used in data warehouse and hive query parsing using antlr to enable on the fly query modification.
  • > Implemented micro service for scheduling query/tag-based reports/visualizations with deduplication and tolerance to data non-availability.
  • > Export of reports to excel with extensive customization. Also involved creation of reports for hierarchies; pivot table exports and computation of summary tables.
  • > Worked on GWT based webapp for adding visualizations(combination charts,heat maps etc) ,creating dashboards,RBAC customizations, speeding up UI loading times, table filtering etc.
Machine LearningScalaSparkAkkaData MungingETL+13

Bmc software

Product Developer

Jul 2009Aug 2012 · 3 yrs 1 mo · Pune

  • > Designed and implemented state machine for task execution in a Release Management tool.
  • > Worked on exposing web services and scale lab testing.
  • > Worked on archival/delete strategy for artifacts.
  • > Overhauled web ui for look and feel; worked on SWT UI for a desktop app.
  • > Worked on an integration project for pulling artifacts to datawarehouse and generating graphs of IT assets.
Web ServicesSWTData WarehousingGraph GenerationSoftware Development

Education

National Institute of Technology, Tiruchirappalli

B.Tech — Computer Science Engineering

Jan 2005Jan 2009

South Point High School

H.S.C

Jan 2005Present

Stackforce found 100+ more professionals with Machine Learning & Data Engineering

Explore similar profiles based on matching skills and experience