Suhit Sukla Baidya
Guwahati
Summary
Enthusiastic Natural Language Processing Engineer adept in NLP modeling, Search/Ranking, and skilled in testing, analyzing, building, deploying models, with a proven ability to translate them into meaningful business metrics.
Overview
3
3
years of professional experience
3
3
Certification
Work History
NLP Engineer
Splore
Bangaluru
04.2023 - Current
- Developed search indexes using hybrid, semantic rank profiles, incorporating concepts such as reranking and a multivector approach.
- Finetuned language models tailored to our domain use case and seamlessly integrated them into our search rank profile.
- Established job pipelines in Spark to extract data from Cassandra, performed transformations, chunking, embedding, and efficiently pushed the data to the search index.
- Collaborated on RAGs and summarization pipelines to enhance search functionalities.
- Integrated Bing results to improve the accuracy of informational rank profile.
- Documented research and analysis methodologies employed in the project for future reference and knowledge sharing.
- Conducted Proof of Concepts (POCs) using Pinecone, Weaviate, and Vespa to explore potential enhancements and advancements in the project.
NLP Engineer
yellow.ai
06.2021 - 08.2022
- Developed ETL and EDA pipelines in Pyspark and Azure Databricks, enabling seamless scheduling with minimal effort.
- Created Analytics pipelines using Pyspark, incorporating Embeddings from USE, XLMRoberta, DBScan, and custom clustering algorithms.
- Deployed Bot performance metrics using opensearch, kafka, and Pyspark, leveraging key insights on user behavior.
- Successfully delivered End-to-End Labeling pipeline with trained models, significantly enhancing labeled data quality.
- Generated Custom Embeddings utilizing GPT-2 language model for both production and analysis tasks.
Data Science Intern
yellow.ai
03.2021 - 05.2021
- Analysis tasks of Insurance domain user data
- Trained,deployed improved small talk model which can handle gibberish text.
Education
BTech Computer Science -
KNIT Sultanpur
05.2019
Skills
- Machine Learning, NLP , Language modelling
- Python, Pyspark
- PyTorch, Tensorflow
- Kafka, NoSQL
- AWS
- Elastic Search, Weaviate, Vespa
Certification
- Deep Learning Specialization - Coursera, 03/2019, 09/2019, https://www.coursera.org/account/accomplishments/specialization/certificate/ESB893TYQH26
- Natural Language Processing Specialization - Coursera, 08/2020, 01/2021, https://www.coursera.org/account/accomplishments/specialization/certificate/AZXLBT9E8637
- End to End Machine Learning with Tensorflow on Google Cloud - Coursera, 08/2020, 11/2020, https://www.coursera.org/account/accomplishments/certificate/QJ5M3YUUW3PH
- Natural Language Processing: NLP With Transformers in Python - Udemy, 01/2022
Hobbies and Interests
- History
- Music
- Manga
- Economics
Timeline
NLP Engineer
Splore
04.2023 - Current
NLP Engineer
yellow.ai
06.2021 - 08.2022
Data Science Intern
yellow.ai
03.2021 - 05.2021
BTech Computer Science -
KNIT Sultanpur
Similar Profiles
Nikita BishnuNikita Bishnu
Content Marketing Executive at The Business Research CompanyContent Marketing Executive at The Business Research Company
Nilotpol KumarNilotpol Kumar
Medical Project Coordinator at IQVIAMedical Project Coordinator at IQVIA
Nursafique AhmedNursafique Ahmed
Senior Engineer-Customer Care at Sysmex India Private LimitedSenior Engineer-Customer Care at Sysmex India Private Limited
Rajat SinghRajat Singh
Intern at Darshika Eco CityIntern at Darshika Eco City
Melis ZerenMelis Zeren
NLP Engineer at Mobildev Inc.NLP Engineer at Mobildev Inc.