Ishita Ankit

Software Engineer

Sunderland, Massachusetts, United States8 yrs 3 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

Strong background in software development and data engineering.
Experience with machine learning and natural language processing.
Proven ability to develop analytical models and data pipelines.

Stackforce AI infers this person is a Software Engineer with expertise in AI and Data Engineering.

Contact

Skills

Core Skills

Software DevelopmentCloud ComputingMachine LearningNatural Language ProcessingData EngineeringData Science

Other Skills

CC++PythonAzureResearchTensorFlowDatabasesUser Interface DesignJavaElastic SearchKafkaData AnalysisTime Series AnalysisMicrosoft OfficeHTML

About

I am a final year graduate student pursuing Masters in Computer Science at University of Massachusetts. I completed my Bachelor's from Indian Institute of Technology, Kanpur with major in Mathematics and Scientific Computing and minor in Artificial Intelligence. You can find my resume at https://drive.google.com/file/d/1CEtlP3lBgYEUO9K-7d5YiuTotp7uThNC/view

Experience

8 yrs 3 mos

Total Experience

2 yrs

Average Tenure

7 yrs

Current Experience

Microsoft

Software Engineer

Jun 2019 – Present · 7 yrs · Redmond,WA

Software Developer in Azure compute CIS(Capacity Infrastructure Service) Provisioning Team.

CC++PythonAzureSoftware DevelopmentCloud Computing

information extraction and synthesis laboratory (iesl)

Graduate Research Student

Sep 2018 – May 2019 · 8 mos · Amherst, MA

Sequential Question Answering, Prof.Andrew McCallum, Prof.Mohit Iyyer.
Working with Question Answering in a conversational context(QuAC dataset). Ongoing work in the direction of co-reference resolution and attention shifting mechanism to answer follow-up questions.

PythonResearchTensorFlowMachine LearningNatural Language Processing

Goldman sachs

Technology Summer Intern

May 2018 – Aug 2018 · 3 mos · New York, New York

Liquidity Risk Technology.
Worked with databases & internal software to create pipeline for automated user input into data lake.
Improved User Interface offering dynamic suggestions, duplicate entry checks, viewing options, pre- processing and post-processing features while populating data to minimize developers’ dependency.

DatabasesUser Interface DesignPythonSoftware DevelopmentData Engineering

Microsoft

Deep Learning Research student

Jan 2018 – May 2018 · 4 mos · United States

Prof. Andrew McCallum, T. J. Hazen, Andrew McNamara (Project mentors)
Explore transfer learning to answer out-of-domain questions using Bi-directional Attention Flow(BiDAF) model. Training on SQuAD dataset and using learned parameters to give good results on Maluuba’s NewsQA dataset.

JavaElastic SearchKafkaSoftware DevelopmentData Engineering

Inmobi

2 roles

Data Scientist Intern

Promoted

May 2016 – Jul 2016 · 2 mos · Bengaluru Area, India

Predicting User Relevant Advertisement, Data Scientist Intern
Analysed data containing app usage history to obtain user specific pattern in preferences.
Tried k-means, agglomerative Mean-Shift & Markov models to group users with similar features.
Trained SVM, decision trees & Random Forest for predicting ads with maximum click through rates to provide user targeted advertisements.

Data AnalysisTime Series AnalysisData Science

Software Engineer Internship

May 2016 – Jul 2016 · 2 mos · Bengaluru Area, India

Demand Pool Analyzer (DPA), Software Intern
Build an Analytical Engine to get insight into Supply-Demand Matching for real time debugging.
Tomcat web application in Java backed by Elastic Search for efficient querying & aggregating.
Real time feedback using Kafka which provided data for analysis from serving systems having
necessary details

Tarnea technology solutions ltd.

Data Analyst Intern

May 2015 – Jul 2015 · 2 mos · Bengaluru Area, India

Sales Forecasting using Time Series Analysis, Data Analyst Intern
Developed a model to predict weekly and quarterly sales of medicines using past 2 years data.
De-trended & deseasonalized the data to obtain stationary sequences for applying time-series models.
Used Exponential Smoothing & ARIMA[Auto Regressive Integrated Moving Average] methods to
forecast the sales of 12 medicines for 30 retail stores.