Now
MSc at Imperial, with ongoing dissertation work on physics-informed operator learning for microbial dynamics.
01 Section
Timeline
The shorter version. Details live on the resume and linked pages.
-
NHCE, Bangalore
B.E. in Computer Science
Graduated in Computer Science with a CGPA of 9.09 / 10.
-
Software Engineer, Oracle Health (formerly Cerner)
Population Health Analytics · Bangalore, India
Built healthcare data pipelines, analytics workflows, and test automation for large CMS-aligned patient datasets.
-
AI Engineer, IBM
Client Engineering · Bangalore, India
Worked between IBM Research and client delivery, turning research ideas into enterprise AI systems and evaluation workflows.
Open -
Impact Scholar, NeuroMatch Academy
Impact Scholar Program - Virtual, Global
Researched biological priors and scaling behaviour in artificial and biological agents through NeuroAI experiments.
Open -
Imperial College London, London, U.K.
Master of Science in Biomedical Engineering
MSc in Biomedical Engineering at Imperial, focused on Computational Bioengineering.
Open -
Dissertation Research, Imperial College London
MSc Computational Bioengineering · Ongoing
Ongoing dissertation on physics-informed operator learning for microbial dynamics under Prof. Reiko Tanaka.
02 Section
How I Work
The kinds of problems I naturally gravitate toward.
Computational Engineering
I like hard technical systems work, especially when it touches biology, research, or messy real-world deployment.
AI for Science
Most of my recent work sits somewhere between applied ML, scientific modelling, and tools that help experts move faster.
Systems Thinker
I usually end up connecting the research, engineering, and decision-making sides of a problem instead of treating them separately.
03 Section
Projects
A few pieces of work that show the range of systems and domains I have worked in.
01
NeuroMatch Academy, July 2023
Prediction of Future Continuous Motion States from ECoG Recordings
Scikit-learn, Pandas, Matplotlib, Research
- Built a data pipeline to analyze ECoG data for correlations between neural signals and cursor movement.
- Achieved a max R-square of 49.3%, with processing latency reduced to 5 milliseconds using techniques like frequency filtering and PCA.
- Identified correlations between Brodmann areas and neural signals, enabling faster processing by targeting specific brain regions.
02
NeuroMatch Academy, June 2022
Adversarial Tweet Sentiment Analysis
PyTorch, HuggingFace, Transformers
- Performed sentiment analysis using SBERT from HuggingFace, reducing high-dimensional data to 3D space with PCA.
- Trained a logistic regression model, validating data compression without loss in prediction accuracy.
- Highlighted classification challenges with slang and Twitter-specific words, identifying model limitations.
03
UT Austin (Virtual), May 2023
Autonomous Ice Hockey Agent
Python, PyTorch
- Developed an autonomous agent to play ice hockey using image-based and state-based approaches.
- Achieved 85% accuracy in ball tracking and over 80% game success through policy optimization with the REINFORCE algorithm.
- Built a data pipeline for training and assembling datasets to optimize the agent's goal-scoring strategy.
04
UT Austin (Virtual), June 2023
Analyzing Dataset Artifacts using ELECTRA
PyTorch, HuggingFace, Transformers
- Developed an NLI model using ELECTRA, achieving 88.24% accuracy and improving predictions by correcting dataset artifacts.
- Designed an error analysis framework, categorizing issues to enhance semantic processing and model robustness.
- Conducted experimental fine-tuning on diverse datasets, improving model generalizability.
04 Section
Publications
Papers, technical notes, and longer work that I have written up properly.
05 Section
Toolkit
What I use most often when I am building, testing, or shipping something.
Build
Model
Work In