Vaishnav Chandak

AI Researcher

Bengaluru, Karnataka, India6 yrs 10 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Expert in large-scale machine learning systems.
Led personalization projects for over 100 million users.
Strong background in AI and data science methodologies.

Stackforce AI infers this person is a Machine Learning expert specializing in consumer internet platforms and data-driven personalization.

Contact

Skills

Core Skills

Machine LearningPersonalizationData ScienceNatural Language Processing

Other Skills

RankingRepresentation learningContextual BanditsDeep LearningGraph embeddingsMulti Armed BanditsAIData ProcessingBig DataPythonNLPLogistic RegressionBeautiful SoupWord2VecPySpark

About

Machine Learning professional with 6+ yrs of experience working on large scale Machine Learning systems, serving 100 million+ users. Worked as a core team member of the Glance (Roposo) Personalization Team to solve the personalization of content for the users of Glance (Roposo) using state of the art techniques like Deep Learning, graph embeddings, Multi Armed Bandits etc. Passionate about using data science to build products and strong eagerness to work with talented and energetic people on promising projects. I am IIIT Gwalior graduate in Information Technology (Integrated B.Tech+M.Tech)

Experience

6 yrs 10 mos

Total Experience

1 yr 10 mos

Average Tenure

3 yrs 11 mos

Current Experience

Meesho

2 roles

Lead Data Scientist

Jan 2025 – Present · 1 yr 4 mos · Bengaluru, Karnataka, India

Solving for cold user recommendations, Remarketing/acquisition feed optimisations, uplift modeling and targeted discounting usecases

Data Scientist - III

May 2022 – Dec 2024 · 2 yrs 7 mos · Bengaluru, Karnataka, India

Working on Homepage personalization for 100M+ meesho users
System design, Engineering to serve personalized recommendation at scale
Homepage Personalization, homepage layout and tiles at Meesho are personalised based on user's interest. I work on improving Homepage relevance using ML disciplines like Ranking, Representation learning and Contextual Bandits.

Inmobi

2 roles

Data Scientist - II

Promoted

Jan 2021 – May 2022 · 1 yr 4 mos

I work on large scale Machine Learning systems, serving 10 million+ users. Worked in the Glance (Roposo) Recommendations Team to solve the personalization of content for the users of Glance (Roposo) using state of the art techniques like Deep Learning, graph embeddings, Multi Armed Bandits etc. We are a full stack team, responsible for data, models, deployment, and uptime.
Skills : Tensorflow/Pytorch, Python, Machine Learning, Big Data, Apache Spark
Industry : Consumer internet platforms (B2C), content recommendation systems

Data Scientist

Jul 2019 – Dec 2020 · 1 yr 5 mos

Worked on building intelligent products on the top of Teleco Data where we ingest, filter, process over 100 TB of data daily and using AI to transform the raw teleco signals into "application-ready" consumer intelligence that can be leveraged safely, securely, and seamlessly.

Glance

2 roles

Data Scientist - II

Jan 2021 – May 2022 · 1 yr 4 mos · Bengaluru, Karnataka, India

I work on large scale Machine Learning systems, serving 10 million+ users. Worked in the Glance (Roposo) Recommendations Team to solve the personalization of content for the users of Glance (Roposo) using state of the art techniques like Deep Learning, graph embeddings, Multi Armed Bandits etc. We are a full stack team, responsible for data, models, deployment, and uptime.
Skills : Tensorflow/Pytorch, Python, Machine Learning, Big Data, Apache Spark
Industry : Consumer internet platforms (B2C), content recommendation systems

Data Scientist

Sep 2020 – Dec 2020 · 3 mos · Bengaluru, Karnataka, India

Trufactor

Data Scientist

May 2019 – Sep 2020 · 1 yr 4 mos · Bengaluru, Karnataka, India

Worked on building intelligent products on the top of Teleco Data where we ingest, filter, process over 100 TB of data daily and using AI to transform the raw teleco signals into "application-ready" consumer intelligence that can be leveraged safely, securely, and seamlessly.

Inmobi

Data Science Intern

May 2018 – Jul 2018 · 2 mos · Bangalore

SDK CONTENT CONTEXT CATEGORISATION MODEL
The goal was to categorize the text which the user is reading on his phone application into wikipedia categories.Knowing the category of the content will help the advertiser in better campaigning and thus this would directly impact the company’s campaigning ability.
Crawled the wikipedia using BeautifulSoup to get the training data for classification.
Performed preprocessing steps which include stopwords removal, lower casing, tokenizing and ignoring tokens that are too small or too big in the corpus and text normalisation .
Used pertained word2vec embeddings to get the embedding vector for the words in the corpus.
Used weighted mean of the embeddings of words in a sentence to get the corresponding sequence embeddings where weights of words were equal to TF-IDF of that word. Also performed label encoding of the target column.
Used Multiclass logistic regression to build the classifierTools: Python, NLP , Logistic Regression, Beautiful Soup, Word2Vec, Selenium
Tools: Python, NLP , Logistic Regression, Beautiful Soup, Word2Vec, Selenium