Aarin Pratap Singh

Data Scientist

India4 yrs 4 mos experience
Most Likely To SwitchAI ML Practitioner

Key Highlights

  • Delivered end-to-end AI/ML solutions with measurable business impact.
  • Achieved 300% increase in user engagement through innovative systems.
  • Mentored junior team members and fostered peer learning.
Stackforce AI infers this person is a Data Scientist specializing in AI/ML solutions for Retail and SaaS industries.

Contact

Skills

Core Skills

Data ScienceComputer VisionMachine LearningNatural Language ProcessingData Analysis

Other Skills

AWS SageMakerAWS SagemakerAnalytical SkillsApache AirflowArtificial Intelligence (AI)BackpropagationBias varianceBigQueryBitbucketCommunicationComputer ScienceData AnalyticsData VisualizationData WranglingDecision Trees

About

Hi, I'm Aarin Pratap Singh, a result-oriented Data Scientist with 3+ years of experience delivering end-to-end AI/ML solutions across computer vision, GenAI, and predictive modeling. I specialize in building production-grade systems that improve operational efficiency, enable intelligent automation, and drive measurable business impact. Beyond my core responsibilities, I actively mentor junior team members and take initiative to support peers—whether it’s optimizing Python scripts, writing APIs, debugging issues, or fostering peer learning through hands-on guidance and knowledge sharing. 🔍 What I Do: Design and deploy full-lifecycle AI/ML systems — from data preprocessing and modeling to inference optimization and monitoring. Solve real-world problems across retail, social media, and SaaS domains using deep learning, NLP, recommendation systems, and GenAI. Collaborate cross-functionally with operations, product, and engineering teams to translate data science into business outcomes. 🚀 Highlighted Work: Vision Transformer (ViT) Classifier on 350K+ images for proof-of-delivery—achieved 83% precision/recall, 250ms inference, and saved 8+ hours/day in manual reviews using GCP & multithreading. Built an ORB/SIFT-based image classification algorithm to detect blank delivery uploads—reduced processing time by 50% while maintaining 95% detection accuracy. Developed a duplicate user identification system using Python, MySQL, and BigQuery—improved targeting precision by 7% in campaign workflows. Created a GenAI-based chatbot using RAG, GPT-3.5 Turbo, and Gemini to query internal databases—automated 90% of manual effort in data retrieval. Designed a feed recommendation engine and personalized notification system using XGBoost and clustering—leading to a 300% increase in user engagement and 280% boost in click-to-engagement ratio. Automated cross-functional reporting pipelines using Jenkins, Bitbucket, and Python; built dashboards on Looker Studio using BigQuery business teams. 🛠 Tech Toolbox: Python · SQL · GCP (Vertex AI, Compute Engine) · BigQuery · Snowflake · MLflow · Docker · Jenkins · MySQL · Django · Scikit-learn · TensorFlow · XGBoost · FastAI · ORB · SIFT · RAG · NLTK · Pandas · NumPy · Airflow · Bitbucket · Linux · Grafana · Bitbucket Passionate about using data science to solve real-world problems and drive meaningful impact. Always open to thoughtful conversations and collaboration—let’s connect!

Experience

4 yrs 4 mos
Total Experience
1 yr 5 mos
Average Tenure
1 yr 9 mos
Current Experience

Reliance retail

Data Scientist (Deputy Manager)

Aug 2024Present · 1 yr 9 mos · Gurugram, Haryana, India · On-site

  • Developed an algorithm to identify duplicate users by combining 30-day activity checks and address-based heuristics using Python, MySQL, and Bigquery; improved duplicate detection accuracy by XX%, optimizing downstream processes.
  • Designed an image verification system for proof of delivery utilizing Python, advanced techniques like ORB, SIFT, and Edge detection with XX% accuracy and XX% recall in classifying blank images and invalid image detection and reducing fraudulent submissions XX%.
  • Automated reports and performance tracker to support operation, category, and business team enabled by Python, Bitbucket, and Jenkins.
PythonMySQLBigQueryORBSIFTBitbucket+3

Virtuous vision

Data Scientist

Jun 2023Aug 2024 · 1 yr 2 mos · Remote

Krishify

Data Scientist

Dec 2021May 2023 · 1 yr 5 mos · Gurugram, Haryana, India · On-site

  • Constructed user’s feed recommendation classifier powered by Python, AWS Sagemaker, and XGBoost with 70% accuracy; resulting in a 300% boost in the engagement matrix
  • Forecasted non-app launch users by utilizing Python, XGBoost classifier with 75% recall rate, leading to a substantial 25% upswing in app launch and 38% in quality sessions
  • Implemented a personalized notification system using Python, Scikit-learn, and K-mean algorithm, yielded a remarkable 30% increasing in CTR , and the consequential impact was a staggering 280% surge in the click-to-engagement ratio
  • Utilized the NLTK library to preprocess text and developed the Multi‑Class Topic Tagging Model using Fastai’s Transformer for text classification, achieving 72% accuracy
  • Conducted performance analysis by utilizing python libraries such as pandas, matplotlib, and seaborn to replace underperforming features, resulting in 10% less cost on production and an increment of 30% in user session time
PythonAWS SagemakerXGBoostScikit-learnNLTKPandas+4

Education

The NorthCap University

Bachelor of Technology — Computer Science

Jan 2017Jan 2021

Stackforce found 100+ more professionals with Data Science & Computer Vision

Explore similar profiles based on matching skills and experience