Kanhaiya Nathani

AI Researcher

Bengaluru, Karnataka, India7 yrs 8 mos experience
Most Likely To SwitchAI ML Practitioner

Key Highlights

  • Increased click-through rate by 25% through innovative targeting.
  • Developed advanced NLP solutions for Samsung's Bixby assistant.
  • Achieved 91% accuracy in number plate recognition project.
Stackforce AI infers this person is a Machine Learning Engineer with expertise in Data Science and Natural Language Processing.

Contact

Skills

Core Skills

Data ScienceMachine LearningNatural Language Processing

Other Skills

AerospikeAirflowAmazon S3Amazon Web Services (AWS)Apache KafkaArtificial Intelligence (AI)Artificial Neural NetworksAssembly LanguageAutomatic speech RecognitionCC++Databricks ProductsDeep LearningDigital Image ProcessingFastAPI

About

IQ level: 117 :p Github: https://github.com/kanhaiyanathani Recent Tech Stack: BigQuery | GCP | Docker | Apache Airflow | Jupyter | Python Working Knowledge: Bixby | NLP | Speech Processing | Statistical modeling | Computer vision | Robots Interests: Ads Monitization | Machine learning | Deep learning | Robotics I am a Machine Learning Engineer (MLE-2) at ShareChat, where I work on the Ads Data Science team to improve the performance of our Ads campaigns through the LookAlike Audience Targeting feature. Prior to this, I worked at Samsung R&D in the NLP department, where I developed various on-device solutions for Bixby, Samsung's virtual assistant. I graduated from IIT Bombay in 2018 with a dual degree in B.Tech and M.Tech. During my final year of study, I worked at the Digital Audio Processing Lab (DAP-Lab) under Prof. Preeti Rao, researching deep learning and statistical learning methods for speech processing. My learning starts with Insertion sort but my curiosity drives me towards quick sort :0

Experience

7 yrs 8 mos
Total Experience
1 yr 11 mos
Average Tenure
3 yrs 2 mos
Current Experience

Makemytrip

2 roles

Lead Data Scientist

Jan 2025Present · 1 yr 5 mos · On-site

Apache KafkaFastAPILarge Language Models (LLM)MLflowDatabricks ProductsPySpark+2

Senior Data Scientist-2

Apr 2023Apr 2025 · 2 yrs · On-site

PySparkPrestoSQLRedashRedisAerospikePrompt Design+5

Sharechat

Machine Learning Engineer - 2

Aug 2022Feb 2023 · 6 mos · Bengaluru, Karnataka, India · Remote

  • Ads Monetization: Led the development and launch of Lookalike Audience Targeting feature, resulting in a 25% increase in click-through rate through A/B testing, and collaborated with cross-functional teams to bring it live on our advertising platform
Google BigQuerydockerData ScienceGitSQLGoogle Cloud Platform (GCP)+3

Samsung r&d institute india

Lead Engineer

Mar 2020Aug 2022 · 2 yrs 5 mos · Bengaluru, Karnataka, India

  • 1. Offline Commands: Slot normalizer for multiple capsules(apps), fully offline/on-device solution, successfully deployed on the latest flagship mobile device(S22), for both English & Korean languages.
  • 2. Contextual NLU - Was responsible for algorithmic design, development and deployment of context based partial matching for visual devices(like TV), were in direct communication with HQ counter-part.
  • Used combination of tri-gram and h-trie methods to reduce the context indexing time from O(n^2) to O(n)
  • Used caching to avoid repetitive computations in the parent module, reducing the run-time latency by ∼70%
  • The solution was deployed for en-US, Korean and European languages after clearing all release cycles
JavaGitPandas (Software)Search Engine Optimization (SEO)C++Python (Programming Language)+2

Samsung electronics co. limited, south korea head quarters

Senior Software Engineer

Jan 2019Mar 2019 · 2 mos · Suwon, Gyeonggi-do, Korea

  • Worked on Robot Skillset Generation and developed 2D Navigation module for robot using Unreal Engine.
  • Used Dynamic-Window Approach(DWA) to calculate "optimal" velocity vectors for smooth navigation,
  • successfully ran both simulated and hardware robot along the user-defined destinations.
  • The project was highly appreciated by Samsung executives at South-Korea(HQ). Also got nominated for
  • Best contributor and Team player awards for this work.

Samsung r&d institute india - bangalore private limited

Senior Software Engineer

Aug 2018Mar 2020 · 1 yr 7 mos · Bangalore, India

  • Named Entity Correction - Developed solutions using multiple fuzzy matching methods like ULA(Universal Levenshtein Automata) or “FAISS by facebook”, corrected ∼30% ASR mistakes on a 20K test data-set
  • Also developed an efficient phonetic matching module using WPSM(weighted phonemic substitution matrix), which further corrected the phonetic mistakes in ASR.
GitImage ProcessingPandas (Software)Machine LearningData Science

Tessact

Data Science Intern

Dec 2016Jan 2017 · 1 mo · Mumbai Area, India

  • Developed a DNN based cascade framework for the reliable detection and recognition of Number plates in a vehicle
  • Trained a region proposal network to identify probable regions of the number plate, followed by a CNN
  • based binary classifier adapted for classifying the identified regions based on existence of number plate
  • Used a Bi-LSTM network in order to generate the alphanumeric sequence written on the number plate, and achieved an overall accuracy of 91% on an in-house dataset
Data ScienceGitImage ProcessingPandas (Software)Machine Learning

Disney research

Data Science Intern

May 2016Jul 2016 · 2 mos · Mumbai Area, India

  • Implemented different models for time-series prediction system including RNN and LSTM, and was able to predict whether the demand for a specific product category would increase or not with 80% accuracy.
  • Developed an end-to-end pipeline for the same, from fetching data from MySQL Database to displaying
  • the prediction results on an interactive GUI
  • Also, proposed the system architecture for consumer-targeted product recommendation system using
  • combination of content-based and collaborative filtering techniques
Data ScienceSQLPandas (Software)Machine Learning

Education

Indian Institute of Technology, Bombay

Dual Degree (Btech+Mtech)

Jan 2013Jan 2018

prestine childrens high school

High School

Jan 2009Jan 2011

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

Explore similar profiles based on matching skills and experience