Jul 2022 – Jun 2025 · 2 yrs 11 mos · Hyderabad, Telangana, India

• Azure (Core) Compute Group, C+AI division

May 2021 – Jul 2021 · 2 mos · Hyderabad, Telangana, India

• Worked in the OneFleet Autopilot team in the Azure Compute Group at IDC, part of the Cloud + Artificial Intelligence division:
• As part of an exercise to consume datacenter inventory in a unified format, updated a critical tool used by Autopilot teams, tenants and services to enumerate fault domains for servers in different datacenters to support both types of inventory formats in use today while we migrate from one to the other. In addition, extended the same tool to work both when run on a developer machine or in the datacenter.
• Used C#, C++/CLI and C++ and Cockpit (for querying)

Jul 2021 – Nov 2021 · 4 mos · Mumbai, Maharashtra, India

• One of the 3 undergraduate TAs selected for the Operating Systems theory + lab courses
• Involved in making quizzes, grading labs and exams and assisting students in their coursework

Dec 2020 – Jan 2021 · 1 mo · Mumbai, Maharashtra, India

• Designed an HR Compliance portal with different functions for different user types, using C#, ASP.NET and MS-SQL
• Features: add/edit user and document category details, upload documents in each category and view them in a repository

Nov 2020 – Dec 2020 · 1 mo · Barcelona, Catalonia, Spain

• Presented a paper I co-authored at the COLING 2020 conference
• Computational Linguistics (COLING) Conference, 2020 | NLP Conference :
• Textgraphs-14: Shared Task on Multi-Hop Inference for Explanation Regeneration:
• Co-authored a publication, developed methods to reconstruct the explanation graph for elementary science questions
• Developed a model with an improvised Information Retrieval using tf-idf vectorizer to rank all explanations in the dataset
• Designed a unique re-ranker using BERT, RoBERTa & SciBERT, got 0.5061 MAP score and were ranked 4th

Apr 2020 – May 2020 · 1 mo · Nancy, France

• CRYPTOGRAPHY:
• Formal Verification of security protocols:
• Studied operational semantics, equivalence properties (in the applied pi calculus and the Tamarin prover) and the SAPIC plugin (tool translating high level protocols to multiset rewrite rules, analyzable by Tamarin)
• Introduced the notion of biprocesses (semantics and translation), and diff equivalence in SAPIC, and worked on the soundness proof of the translation after the addition

Dec 2019 – Jan 2020 · 1 mo · Hyderabad Area, India

• DEEP LEARNING :
• Applying NLP techniques to Time Series Analysis for Stock Futures :
• Designed and implemented an intuitive approach to storing the history of a stock in the form of a vector using a Ticker Embedding Model, similar to that in a Word Embedding model, representing the meaning and context of the word. The ticker embedding hence represents the past movement of a stock and clusters similar stocks. The corpus was constructed using features: Price, Volume, Open Interest, Asset Class and Exchange
• Incorporated a number of technical indicators such as Momentum, Trailing Volatility, Asset Class and average return across each asset class along with these embeddings for time series analysis
• Designed, tested and trained an LSTM classifier (built using PyTorch) to map a time series of the Expected Return of multiple stock tickers to predict the Expected Return and to study non linearity and inter asset class correlation
• Expanded the base LSTM to incorporate attention, and retrain over the latest data while testing
• Optimized the hyperparameters of the network using the Python Ray library for Grid Search and Hyperopt for Bayesian Hyperparameter optimization
• Awarded a Letter of Recommendation for exceptional performance shown throughout the internship
• TRADING ALGORITHMS : Implementation in Python
• Worked towards developing, modifying and implementing PAIRS, Betting against Beta and Momentum trading algorithms on the Indian Stock market
• Beta was calculated by regression on the CAPM equation :
• > The strategy was implemented with daily, weekly and monthly rebalancing of the portfolio with a 6 month rolling window
• > Performed and anaylzed the difference in output on equal weighted and value weighted portfolios
• Modified the PAIRS trading algorithm on a rolling window of 1 year with 12% CAGR and 0.71 overall Sharpe ratio in Python

Jul 2019 – Nov 2019 · 4 mos · Mumbai, Maharashtra, India

• Only sophomore to be selected for TA-Ship for the Computer Programming and Utilization course (CS101) for freshmen
• Involved in making questions, solutions and testcases for the labs, teaching and assisting students in and outside lab hours

Jun 2019 – Jul 2019 · 1 mo · Kolkata Area, India

• Analysis of underperforming stores given all KPIs and SKUs (Stock Keeping Units) level data :
• Statistical Analysis of transactional data at store level to understand and attribute reasons for de-growth using Pandas, Sqlite and the various graph visualizations in Matplotlib
• Given all KPIs with respect to category, used deep dive into individual SKU level performance to come up with solutions to counter degrowth, in the MGF Gurgaon Hyper store and the Vizag Hyper store

May 2019 – Jun 2019 · 1 mo · Kanpur Area, India

• Analysis of ML Algorithms for Spam Email Classification in Python :
• Analysed KNN, Naive Bayes, SVMs and Neural Networks and finally implemented Naive Bayes and KNN for the classification of various data sets into spam and ham
• Compared accuracies of these methods for various data sets and categorised the best method for different data sets

Nov 2018 – Dec 2018 · 1 mo · Kolkata Area, India

• Configured and enhanced the features of a Chatbot for Paylite Leave applications (on LUIS platform)
• Suggested essential metrics for the BOT and helped in introducing VOICE to TEXT feature in chatbot (using BING API) from Microsoft Azure
• Research on Human Resource Automation and comparative study between chatbots and other developments in Google Assistant, IBM Watson, Alexa and Cortana