ML systems/Computer vision/LLM engineering/Aachen, Germany
I train segmentation models on data nobody has labelled yet, and build LLM systems that mark their own uncertainty instead of asserting through it.
A
Raw inputWhat the microscope gives you.
B
Ground truthHand-annotated in napari, one label per bouton.
C
PredictionFine-tuned MicroSAM, never saw this volume.
Measureda real number from a real runShippeddeployed and usable now, in production or hostedPendingnot measured yet, and says soNot shippedbuilt, measured, left out on purpose
Instance segmentation of synaptic boutons in Drosophila brain microscopy, and the tool that ships it to the lab
Raw input
Ground truth
Prediction (held out)
Fine-tuned MicroSAM (vit_l_lm) on a held-out volume. Each colour is one predicted bouton instance.
A fully reproducible deep-learning pipeline that segments and quantifies synaptic boutons in confocal Z-stacks of the Drosophila mushroom body calyx, plus BoutonViewer: the napari desktop tool that puts the model in the hands of the biologists it was built for. Research and delivery as one project, because a model nobody can run is not a result.
Fine-tuned MicroSAM (vit_l_lm) with custom post-processing on a hand-annotated 3D dataset built from scratch in napari
Benchmarked four SOTA 3D instance-segmentation backbones head to head: Cellpose 3D, nnU-Net v2, StarDist 3D and SwinUNETR
Trained across three preprocessing variants (raw, difference-of-Gaussians, PSF-deconvolved) and evaluated with instance-matching metrics that account for physical voxel volume, not pixel counts
BoutonViewer reports per-bouton volume and surface area in µm³ / µm², auto-derives voxel calibration from acquisition type, and lets a biologist click away a false positive without touching code
Final checkpoints published on Hugging Face for reuse
LLM systemsShipped06/2026 – present · Solo project
TechDrishti
An agentic AI workflow for Hindi tech journalism, running unattended every day on GitHub Actions
A fully autonomous newsroom. Every morning it collects English tech news, decides for itself what is genuine news versus a job listing or SEO spam, calls out to its own research agent for anything a keyword search cannot answer, and writes an original Hindi article per story through a multi-stage LLM pipeline. Not machine translation. Zero servers, zero hosting cost.
Agentic multi-stage plan-execute pipeline across sarvam-30b/105b, engineered around real token-starvation and hallucination failure modes found in production, not anticipated in design
Cheap-model triage filters non-news before the expensive model ever sees it, which is what makes the economics work at roughly a cent per run
Persistent entity cache with a 45-day TTL and sense disambiguation, so the same name is never researched twice
Sentence-embedding clustering merges duplicate coverage of one story across 8 RSS feeds and GitHub trending
Every fix documented as claim, root cause, fix, verified on real articles, rather than a green test
LLM systemsShipped06/2026 – present · Solo project, spun out of TechDrishti
Deep Research Agent
An autonomous ReAct agent that plans its own searches and enforces grounding in code, not in a prompt
An autonomous ReAct agent that plans its own searches, reasons over what each result adds, and decides for itself when the evidence is enough — then returns a cited report with every comparison claim verified in code, not just promised in a prompt. It began as a free-search extension for TechDrishti and grew into a standalone, four-mode system: ask, quick grounded answer, research an article, and an automated Hindi article writer. Live and usable on Hugging Face Spaces.
Code-enforced iteration budget (MAX_ITERATIONS = 8): when it is exhausted the search tools are forcibly removed, but calculate survives so the report can still finish
A grounding check flags any comparison claim whose named target was not found in retrieved sources, because two rounds of increasingly explicit 'don't hallucinate' prompting failed reproducibly
AST-based calculator, structured tool errors, and evidence-tool separation, so a fabricated number cannot launder itself into looking grounded
Measured against TechDrishti integration and consciously left out of production. The case study does not spin that as a win
Free keyless retrieval layer (DuckDuckGo + Google News RSS + page/PDF fetch) instead of a metered search API
Vision + LLMPending07/2026 – present · Solo project
Chitragupta
A hands-free camera assistant where one model writes the brief for the other model's eyes
A voice assistant that watches through a phone camera while your hands are busy — tracking steps, substitutions and timers, and speaking back. Two models split the job: one converts frames to text and nothing else, the second does all reasoning and tool calling and never sees a pixel. That split exists because a single-model design could not survive its provider's per-minute cap, and the whole system is engineered to run continuously inside a 200,000-token daily ceiling on free tiers.
Hybrid pipeline (Groq Qwen3.6-27B for vision, DeepSeek v4-flash for reasoning + 10 native tools), forced by an 8,000 token/minute cap that made a one-model design impossible
The reasoning model writes its own brief to the vision stage, so the system can look for things nobody anticipated in advance — and asks for observations, never judgements
Cost engineering measured, not guessed: a browser-side perceptual diff gate drops unchanged frames before any request, and an opt-in close-up tier costs a measured 2.4× per frame
Persisted task and timer state on disk, injected into every prompt, so a restart loses nothing and timer checks cost no inference
Verified against a real 40-minute phone session, with two known failure modes documented rather than hidden
Led a team of 3 building a real-time human detection system to help enforce COVID-19 distancing restrictions, combining object detection with geometric distance estimation.
Real-time human detection using YOLOv3
Perspective transformation to convert image-space distances into real-world distances between individuals
The napari desktop tool that puts the thesis segmentation model in biologists' hands
The delivery half of the thesis, packaged as its own tool: a napari app that runs the bouton-segmentation pipeline on a confocal or Airyscan stack, reports per-bouton volume and surface area in µm³ / µm², and lets a biologist delete a false positive without touching code. A step-by-step usage manual lives on the repo's GitHub wiki.
One-file-in, table-out workflow for non-programmers, with prediction caching so a display change never re-runs inference
Usage manual and model/data notes shipped alongside the tool, including where the model should not be trusted
04/2024 – 07/2025 · Interdisciplinary lab course with Celonis
Cohort Discovery & Analysis Web App
Cohort discovery on event data — a proof-of-concept built for Celonis
A proof-of-concept for Celonis: an event-data application that segments event logs into behavioural cohorts by implementing a cohort-discovery research paper — data clustering over event sequences, then interactive analysis of the cohorts it finds. A light LLM assist sits on the analysis options, but the work is event-data mining, not an LLM system.
Full-stack app in React + Flask, tested with PyTest, for filtering, visualizing and comparing discovered cohorts
Software Engineering Group, RWTH Aachen University
Building a fully reproducible deep-learning pipeline to segment and quantify synaptic markers in confocal microscopy of the Drosophila mushroom body calyx — fine-tuning MicroSAM and benchmarking it against Cellpose 3D, nnU-Net v2, and SwinUNETR. Supervised by Prof. Dr. Abigail Morrison, with Prof. Dr.-Ing. Johannes Stegmaier as second examiner.
07/2024 – 05/2025
Student Assistant — Computer Vision Research
Institut für Industrieofenbau und Wärmetechnik, Aachen
Researched monocular metrology methods for measuring hot heel depth in an Electric Arc Furnace. Built Python/OpenCV tools for industrial computer vision applications and supported PhD candidates with data collection and analysis.
06/2021 – 03/2023
Quality Engineer
Larsen & Toubro Infotech, Hyderabad
Delivered an automated testing framework (Python + Selenium) from proof-of-concept to production, improving testing efficiency by 50%. API testing with Postman; trained junior engineers on testing methodology.
06/2020 – 07/2020
Intern
Ramrao Adik Institute of Technology, Navi Mumbai
Managed a team of 5 building a mobile test-taking app in Flutter/Firebase, including GPS-based authentication and UI design end to end.
Education
10/2023 – 09/2026 (expected)
M.Sc. Data Science
RWTH Aachen University
Focus: Computer Vision, Data Science, Machine Learning. Grades — Machine Learning: 1.7, Business Process Intelligence: 1.7, Advanced Process Mining: 1.7, Intro to Data Science: 2.1.
09/2017 – 05/2021
B.Sc. Computer Engineering
University of Mumbai
Final grade 8.42/10. Focus: Software Development, Software Engineering, Machine Learning.
