Arnab Chakraborty

Data Engineer

Bengaluru, Karnataka, India10 yrs 2 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Expert in Machine Learning and Data Engineering.
Proven track record in AI software development.
Strong experience in predictive modeling and data analytics.

Stackforce AI infers this person is a Data Science and Engineering expert in the Technology sector.

Contact

Skills

Core Skills

Data EngineeringMachine LearningData Science

Other Skills

MLOpsDatabricksMicrosoft Azure Machine LearningPython (Programming Language)PySparkSQLAzure BatchAzure DataFactoryAzure Key VaultAWS SageMakerAzure DatabricksPythonSplunkAWSTensorFlow

About

Key Skills - Python (Numpy , Pandas, Scikit-learn, XGBoost, Tensorflow, Keras, Spacy ,Pytorch ,Rasa, Flask), Pyspark, R language, SQL, Mongo DB, HIVE, Advanced Excel, Tableau, Power BI, Splunk, Databricks , AWS Sagemaker, Azure Datafactory, JENKINS, Docker, Github, Javascript, HTML and CSS. Data Science Skills- Machine Learning , Supervised, Unsupervised, Predictive Modelling, Statistics, A/B Testing, Hypothesis Testing, Exploratory Data Analysis, Data cleansing, Data Visualization, Model Deployment, Neural Networks, Deep Learning, Text Mining, Natural Language Processing(NLP) Algorithms - Linear Regression, Regression Analysis, Classification, Logistic Regression, Decision Tree, Random Forest, Support Vector Machines(SVM), Naive Bayes, Xgboost, Principal Component Analysis(PCA), all variants of Convolutional Neural Network(CNN), RCNN Family, YOLO series, RNN, LSTM, Auto Encoder Decoder Transformer based model and Generative AI Models.

Experience

10 yrs 2 mos

Total Experience

1 yr 8 mos

Average Tenure

3 yrs 10 mos

Current Experience

Intel corporation

2 roles

Data Engineer (Data Scientist)

Sep 2023 – Present · 2 yrs 8 mos · Bengaluru, Karnataka, India

MLOpsDatabricksMicrosoft Azure Machine LearningPython (Programming Language)PySparkSQL+5

AI Software Development Engineer

Jul 2022 – Sep 2023 · 1 yr 2 mos · Bengaluru, Karnataka, India

Working as a Data Scientist in Intel Bluetooth team, an active member of LE Audio feature
release and contributed to LE Audio quality control and improvement.
Data based Business decision using Python, SQL, Splunk, Telemetry Data Analytics development
AI Approach to Data: Apollo based Pre-Processing engine development in Python, AWS
Pipes/Data management and data transformation using Pyspark in Databricks.
Live Audio quality prediction and call drop reason prediction for bluetooth Earbuds .
Advanced Dashboarding and Reporting: KPI, KEI, Statistical, Time Analysis, Other Low level RCA .
Deriving Cross Correlation between FW,HW,SW, OS based on Telemetry Event Logs.
Anomaly Detection for headset Battery drain rate and headset call drop rate

Microsoft Azure Machine LearningSQLDatabricksPython (Programming Language)AWS SageMakerAzure Databricks+4

Epam systems

Senior Data Analyst

Jun 2021 – Jul 2022 · 1 yr 1 mo · Bengaluru, Karnataka, India · Remote

Worked as a Data Scientist for Canadian Tire Corporation.
Built a Bi-directional LSTM model which is able to predict more than 150 classes with 95% accuracy for
classifying various E-commerce Application log.
Trained tensorflow based NLP model in azure Machine learning ,deployed in a azure container registry and published as a service endpoint
for continuous prediction(Azure MLOps).
Worked with Azure DataFactory and DataBricks for data extraction and data transformation respectively.
Used lots of core NLP technique like Spacy 3 NER model ,chunking and chinking for creating custom label from log data.
Using Sumo logic to process streaming log data of different application.

TensorFlowNLPAzure Machine LearningDataBricksSpacyData Science+1

Ust global

Associate III - Data Analysis

Apr 2019 – Jun 2021 · 2 yrs 2 mos · Bengaluru Area, India

. Working employee faq chatbot using a Deep neural network model with 97% accuracy.
. Giving corporate training on Data Analytics
. Converting Jenkins build log data into a structured meaningful table data format and sending it to Splunk, then extracting meaningful insight from build error data and creating an interactive dashboard using Splunk.
. Creating alert and email notiﬁcation using Splunk.
. Created Power BI report for axon crash data.
. Developed a Classiﬁcation model for identifying test run using the SVM technique successfully for proof of concept.
. Working on production data to develop Classiﬁcation model for predicting the status of the test run on diﬀerent hardware setup and model deployment for Intel
. worked on image classiﬁcation model achieved 82 percent accuracy on test data an er implemented random forest using texture analysis by calculating glcm properties for each image classify the diﬀerent ﬂaws on steel plate image problem statement

Myntra jabong

Data Analyst

Dec 2018 – Apr 2019 · 4 mos · Bengaluru Area, India

. Working on the supply chain management system.
. Finding Root cause analysis for each non-compliant steps.
. Data extraction and manipulation of a huge volume of data and simplifying it R for better understanding.
. Maintaining and tracking product flow from inventory to logistics and inward to inventory.
. Implementing Tableau to visualize and understand data more clearly.
. Working with diﬀerent stakeholders, identify and analyze their report.

Cerner corporation

System Engineer(Data analyst)

Aug 2017 – Dec 2018 · 1 yr 4 mos · India

. Text analytics with R programming Loading the data and initial data cleaning
Some initial data analysis, feature engineering, and data visualization
. Training classification models using textual data
. Evaluating the accuracy of the trained classification models
. Optimizing our model for the best generalizability on new/unseen data.
. Connecting Database connection through R programming, creating data visualization on live data
. Cluster analysis on text data
. Creating Regression model in R linear, logistic, Poisson
. Analyze the domain issues on data from the Jira server.
. Visualizing data using Tableau for better understanding and to make it interactive. Create dashboards using Tableau Dashboard and representing the properly cleaned data from the database.
. Develop Scorecard from diﬀerent perspectives like performance analysis of associate Monthly, quarterly, analyze diﬀerent types of issues with respect to diﬀerent domains in Organization.
. Derive the performance scales of employees on issues and help in finding most o en issues of domains.
. Prepare and present the reports with charts to highlight the important analysis point.
. Identify and analyze the reports and help the manager to identify to most o en issues.
. Responsible for acquiring the domain data from primary and secondary sources and maintain the databases and create an analytical framework.
. Monitor an eﬀective timeline to resolve particular issues within the organization.

Ibm india private limited

Technical Specialist

Feb 2016 – Jul 2017 · 1 yr 5 mos · Bangalore,Karnataka

. Utilize and analyze on Extracted data from diﬀerent data sources and diﬀerent teams.
. Extracted, compiled, tracked data, and analyzed data to generate reports.
. Using histograms, running records, and process behavior charts to analyze business data.
. Coordination with the client for updates and troubleshooting.
. Coordination with the team for better eﬀiciency.
. Analysing System log through pig script.
. Analyze the eﬀiciency of the process and depending on that automated the manual process.