Harsh C.

Associate Consultant

Gurugram, Haryana, India4 yrs 6 mos experience
AI ML PractitionerAI Enabled

Key Highlights

  • Pioneered data intelligence in entertainment analytics.
  • Developed automated lead allocation systems for Samsung.
  • Expertise in real-time video processing and cloud solutions.
Stackforce AI infers this person is a Data Engineer specializing in Fintech and Media & Entertainment sectors.

Contact

Skills

Core Skills

PythonAwsData Engineering

Other Skills

SQLAWS MediaLiveMREOpenSearchECSFFmpegPySparkAWS GlueS3LambdaSNSSESEventbridgeMS SQLLinux Server

About

Working at the intersection of GenAI and Data Engineering, leveraging LLMs to solve diverse real-world use cases. Early Innovations & ML Foundation Pioneered data intelligence in entertainment analytics, building sophisticated scraping architectures for platforms like BookMyShow, Paytm, IMDb, and YouTube. Led ML-driven forecasting models that accurately predicted Day 1 box office performance for blockbuster releases including Doctor Strange, Thor, and Brahmāstra. Later transitioned into building Customer Data Platforms (CDP) and data migration pipelines for enterprises, including a major Indian bank. Designed cloud-native solutions on AWS, implementing event-driven architectures with Glue, Lambda, EventBridge, and SNS/SES. Drove analytical transformation initiatives that enabled data-driven decision-making at scale. Managed seamless migration from on-prem systems to the cloud using AWS Glue, S3, Lambda, EventBridge, and SNS/SES, with PySpark and Python as core processing tools.Primarily focussed on analytical requirements of bank. Explored real-time video processing using AWS MediaLive, Media Replay Engine (MRE), and HLS manifest-based workflows. Implemented pipelines for shot detection, score analysis, and OpenSearch indexing, with extensive use of FFmpeg for media transformations.Product had business usecase around Sports Realtime video processing & media companies processing livestreams at scale. Also Previously was part of project where we built a self-learning lead allocation system for Samsung that dynamically optimizes campaign-to-store assignments using configurable rule engines, proximity algorithms, and historical pattern analysis Tech Stack: Python | PySpark | SQL | Linux | AWS (Glue, MediaLive, Lambda, S3, MRE, EventBridge, SNS, SES) | OpenSearch | GCP BigQuery | FFmpeg | MS SQL |.

Experience

Statusneo

Consultant

Oct 2024Present · 1 yr 6 mos · Gurugram, Haryana, India · Hybrid

  • Working at the intersection of GenAI and Data Engineering, leveraging LLMs to solve diverse real-world use cases. Creating Research documents with insights produced from raw data in the db.
  • Real-time video processing using AWS MediaLive, Media Replay Engine (MRE), and HLS manifest-based workflows. Implemented pipelines for shot detection, score analysis, and OpenSearch indexing, with extensive use of FFmpeg for media transformations.
  • Accelerated performance by transitioning CPU-based components to GPU-based instances.
  • Processing videos through HLS manifest files, performing real-time segmentation, feature extraction, shot detection, and score detection, and indexing the results into OpenSearch and other databases..
  • Stack -Python, SQL, AWS MediaLive , MRE(Media Replay Engine) , OpenSearch , ECS(Explored GPU supported instances for achieving low latency)
PythonSQLAWS MediaLiveMREOpenSearchECS+1

Pivotroots

4 roles

Backend Engineer (Data)

Promoted

Feb 2023Oct 2024 · 1 yr 8 mos

  • Building CDP For a leading Indian Bank ||
  • Data Migration from various sources to cloud.
  • Tech Stack - Pyspark , Python , AWS (Glue , S3, Lambda , SNS , SES , Eventbridge) , DBs( NoSql , Sql , documentdb).
  • Used Redshift at scale.
  • Worked on many custom analytics report generation pipelines.
  • Heavily used AWS Glue to process huge amount of data.
  • Developed an Automated Lead Allocation System for the world's largest mobile phone brand(Samsung). This system manages the entire lead lifecycle, from lead collection to enhancing its credibility with a score based on previous purchase history. The leads are then allocated to the required store or Epromoters. Leads are allocated to the nearest store & stores which have the capacity to cater new leads are considered based on user pincode dynamically.This streamlined the process for samsung, providing an automated, configurable flow based on campaigns.
  • Tech Stack used - Python , SQL , MS SQL(db) ,linux , VM , Php
PySparkPythonAWS GlueS3LambdaSNS+6

Associate Backend Engineer (Data)

Promoted

Jun 2022Feb 2023 · 8 mos

  • Movie Solutions through ML/AI.
  • Made End to end data pipelines for easy data flow.
  • Consulting in BigMovie Releases like Doctor Strange , Thor , Brahmastra.
  • Central Log Monitoring System for all scheduled pipelines running on EC2 & GCP Bigquery.Usee logzio for visualisation & alerts.
  • Developed Email to Bigquery Configurable pipeline to handle any types of file for easy reporting.
PythonLinux ServerShell ScriptingSQLData Engineering

Data Analyst

Apr 2022Jun 2022 · 2 mos

Python

ML Enthusiast (Previously Deepflux)

Aug 2021Apr 2022 · 8 mos

  • Worked on setting up scrapping & ml models for Boxoffice day1 revenue prediction
Python

The sparks foundation

Data Science and Business Analytics at The Spark Foundation

Jun 2021Jul 2021 · 1 mo · Noida

Python

Accel knowledge

Survey Analytics

Jun 2019Jul 2019 · 1 mo · Noida, Uttar Pradesh, India

Python

Education

Galgotias College of Engineering and Technology

Bachelor of Technology - BTech

Prelude Public School ,Agra

Schooling

Stackforce found 100+ more professionals with Python & Aws

Explore similar profiles based on matching skills and experience