May 2024 – Jun 2024 · 1 mo · North Goa, Goa, India · On-site

• Project 1:- Built a data-driven thermal predictor using time-series features (current, voltage, cell/temp sensors, SOC) and anomaly detection, enabling early hotspot detection up to [2 minutes] before threshold conditions.
• Implemented a control policy (model-predictive control with learned surrogate / reinforcement learning agent) that optimizes cooling actions and charge rate; validated in simulation to reduce projected degradation under fast-charge cycles by [25 %].
• Integrated battery degradation cost into an economic model and produced CAPEX/OPEX tradeoff tables showing payback scenarios for active cooling hardware versus replacement savings under fleet operations.
• Conducted lifecycle-impact analysis comparing conservative vs aggressive charging strategies; reported metrics per vehicle-km (CO₂e) and cost-per-km under multiple grid-carbon and price scenarios.
• Packaged results into an interactive dashboard and policy brief with actionable recommendations for fleet managers (recommended charge-curves, cooling setpoints, and investment thresholds).
• Project 2:- Researched and developed a digital twin of a small-scale assembly line by integrating IoT sensor data, discrete-event simulation, and predictive analytics. The system enabled real-time monitoring, predictive maintenance, and adaptive control, leading to a simulated ~20% improvement in Overall Equipment Effectiveness (OEE).
• Designed a discrete-event simulation model to replicate workflows, constraints, and machine dynamics.
• Integrated synthetic IoT data streams to mirror live production states.
• Applied predictive analytics for defect detection, maintenance scheduling, and throughput forecasting.
• Demonstrated Industry 4.0 benefits in an operations-management context (availability, performance, quality).
• Conducted as a desk-based study grounded in academic literature, validating the feasibility of digital twins for smart manufacturing.

Nov 2023 – Dec 2023 · 1 mo · Bhubaneswar, Odisha, India · On-site

• During my internship at IIT Bhubaneswar, I engaged in diverse projects aimed at advancing lithium-ion battery (LIB) technology. The primary focus was on overcoming challenges related to energy density, current rate capability, and safety concerns in LIBs, particularly those hindering the widespread adoption of electric vehicles.
• My research work delved into the critical issues impeding the scalability of lithium-ion batteries for electric vehicles. Through the development of silicon-graphite composite anodes and an in-depth exploration of nanostructured silicon materials, the aim was to push the boundaries of energy density and overall performance.
• Project 1: Silicon-Graphite Composite Anode Development
• Objective: Enhance the energy density of graphite anodes while addressing the large volume expansion issue of silicon during lithiation.
• Methodology: Synthesized porous silicon through a novel two-step chemical etching of Al-50 Si alloy, creating a silicon-graphite composite anode. Utilized an environment-friendly water-based slurry for anode preparation.
• Significance: Investigated the impact of silicon particle size and surface oxide layer thickness on lithium diffusion within the composite anode, aiming to improve overall battery performance.
• Project 2: Advancements in Anode Materials for LIBs
• Background: Explored the limitations of graphite anodes and the potential of silicon as a replacement material.
• Research Focus: Investigated the challenges associated with silicon anodes, including high volume expansion and unstable solid electrolyte interphase (SEI).
• Strategies Explored: Examined various strategies, such as nano-sized silicon anodes, to mitigate issues related to stress, strain, and SEI formation.
• Benefits and Drawbacks: Explored size-controlled materials, emphasizing the potential advantages of nanostructured silicon anodes for improving electrochemical performance.

Sep 2023 – May 2024 · 8 mos · Sambalpur, Odisha, India · Remote

• Worked on "Quantitative Analysis of Stock Market Crash Risk Using Statistical and Machine Learning Models "
• Developed a Python-based financial risk assessment model to analyze 87,162 firm-year observations (1995–2008) for stock price crash risk using statistical modeling and machine learning techniques.
• Implemented an expanded market model regression to estimate firm-specific weekly returns (Wj,t) using lagged and lead market index terms, refining the model for non-synchronous trading corrections.
• Calculated crash risk measures including CRASH, NCSKEW, and DUVOL:
• CRASH: Identified firm-year instances with weekly returns 3.2 standard deviations below the annual mean, indicating high-risk periods.
• NCSKEW: Computed negative conditional return skewness using the third central moment of returns, capturing asymmetric risk.
• DUVOL: Derived the down-to-up volatility ratio to assess the likelihood of extreme downside events.
• Processed and analyzed financial datasets using Pandas, NumPy, and SciPy, applying advanced data filtering techniques to exclude firms with non-positive book values, asset distortions, and insufficient trading weeks.
• Automated risk assessment pipeline using vectorized computations and parallel processing, reducing data processing time by 40 percent, optimizing crash risk identification.
• Visualized financial risk trends with Matplotlib and Seaborn, generating firm-wise risk distribution plots, enabling predictive modeling for portfolio risk mitigation.

Jun 2023 – Sep 2023 · 3 mos

• This project used machine learning algorithms to predict pregnancy issues and improve mother care. Data was collected from community hospitals, maternal health care institutions, and clinics using IoT-based risk monitoring system centers. Over 1000 pregnant patients were analyzed using age, blood pressure, blood sugar, heart rate, and temperature metrics. Data visualization was used to provide summaries, overviews, and trends of issues. The dataset was preprocessed using cleaning, featuring, handling, feature, and encoding to increase accuracy for machine learning. The best model was used to predict the condition, which was then used to predict issues in real-world scenarios. The data was imported into Kaggle and included statistics and details about the patient, such as age, blood pressure, and blood sugar. The process involved visualization, pre-processing, multiple models, and contrasting models to identify the most accurate model.

Jun 2023 – Aug 2023 · 2 mos · Guwahati, Assam, India · Remote

• Worked on a research project on determining representative structure, predicting functionalization, and cause of defects in Graphene oxide using machine learning algorithms , data science and molecular simulations.
• The study explores the surface functionalization of graphene oxide (GO) with 1-cysteine, a potential candidate for bio-sensing and biomedical synthesis. Characterization using Raman, Fourier-transform infra red, and dynamic light scattering spectroscopy revealed varying particle size distribution. Classical all-atom simulations revealed a disulfide bond between Cys-GO sheets stabilizes structural dynamicity. This interaction with water molecules introduces variable deformation, allowing for more inter-sheet interactions and reduced random movement.

May 2023 – Jul 2023 · 2 mos · Raurkela, Odisha, India · On-site

• The project I worked on during my summer internship at Koel Fresh Private Limited focused on the implementation of IoT digitalization in cold storage facilities. The main objective of the project was to leverage Internet of Things (IoT) technologies to enhance the efficiency, productivity, and sustainability of cold storage operations. The project aimed to revolutionize traditional cold storage practices by integrating smart sensors, data analytics, and remote monitoring capabilities.

Sep 2022 – Nov 2022 · 2 mos

• Supervised the working of the assigned clubs and their events and ensure that the execution of various events went smoothly. Ensured
• the proper budget according to requirements and availability by negotiating and providing better options for running the event. Coordinated with other teams to integrate, working as a coordinator to serve where and when required.

Jul 2022 – Feb 2023 · 7 mos · Remote

• Became part of the Executive Student Committee (ESC), the Institute's only student-run committee to help Student Chapters get the most out of AIChE. Specifically, I contributed to activities like:-
• Improvement of other Student Chapters.
• Encouraging inter-chapter communication.
• I was the liaison between Student Chapters, AIChE staff, and the Student Chapters Committee (SCC).
• Motivated Student Chapter members to be active in other aspects of AIChE.
• Encouraged Student Chapter members to continue their relationship with AIChE beyond graduation.
• Actively worked in various conferences and events conducted by the conference experience subcommittee.

Jul 2022 – Jan 2023 · 6 mos

• Working as a content, management, and chem e‐car team member
• in the AIChE Nit Rourkela student chapter and coordinating with the
• ESC to serve as a conference experience subcommittee member in
• AIChE global. Managing various events, writing scientific blogs, and
• working in chemical labs to prepare multiple projects are some of my
• responsibilities here

May 2022 – Jan 2023 · 8 mos · Raurkela, Orissa, India

• The Chem-E-Car project is a student competition in chemical engineering where teams design and build small cars powered by chemical reactions. These cars are typically fueled by chemical energy sources like batteries or chemical reactions such as fuel cells. The main objective is to construct a car that can carry a specific load (often represented as weights) and travel a predetermined distance autonomously. Teams need to carefully control the chemical reactions to ensure the car stops at the correct distance. It's a hands-on educational project that combines engineering, chemistry, and teamwork to create innovative and efficient vehicles.
• Experienced working on the Chem-E-Car project. Using Al-air batteries and thermocouples for propulsion, as well as an iodine clock reaction to stop the car, showcases the application of chemical reactions for both power generation and control. Testing the car under various constraints, such as weight and pressure, likely involved optimizing the chemical reactions and the car's design to ensure reliable performance. This project demonstrates the practical application of chemical engineering principles and teamwork to create a unique, chemical-powered vehicle.

Jan 2022 – Mar 2023 · 1 yr 2 mos · Raurkela, Orissa, India

• Prepared ppt on JWST telescope for AIChE K12 session and then was a part of the hosting team for the 11-12th session.
• Been a part of the Super-o-chemicals event organizing team for inno 2021.
• Wrote content for the Man's Muse article series on the topic of submarines, along with its Instagram and WhatsApp captions.
• Prepared the complete video along with editing and contents of the video on the Vizag gas leak as a video team member of the decoding disaster series.
• Wrote Instagram and WhatsApp captions for the Decoding disasters series.
• Prepared 4 question sets as chem e jeopardy team member.
• Wrote Instagram and WhatsApp captions for rules and gameplay, day one and finals of chem e jeopardy event.
• Volunteered for Karyashala in offline mode.
• Completed the safety course ELA199 and earned the safety certificate for chem e-car by AIChE.
• Studied a research paper and viewed a few videos on chem e-car.
• Been a part of a virtual meet with AIChE ICT-IOCB.
• Wrote Instagram and WhatsApp captions for AIChE TIET virtual meet.
• Been a part of the ppt preparation team for SRC pitching.
• Currently representing our student chapter in the AIChE ESC conference experience subcommittee.
• Drafted a blog on Time Crystals.
• Wrote insta caption for induction poster 2022.
• Prepared a sample video on the Beirut explosion as a rough idea for decoding disaster series to show my editing skills.
• Contributed ideas for events.
• Actively worked in content, management, and chem e-car team.

Jan 2022 – May 2022 · 4 mos

• Prepared content and managed various events related to ceramics
• and material sciences. I have been part of multiple seminars and sessions by various industry experts to gain knowledge of ceramics in machine learning and material informatics.