IIT Bhilai · B.Tech, Data Science & Artificial Intelligence · 2027

Kinshuk
Gupta

Building systems that see, reason, and decide
from satellite orbits to emotional intelligence.

AI/ML engineer at the intersection of research depth and engineering rigor. Twice selected for ISRO problem statements at Inter IIT. 2000+ DSA problems solved. I don't just write models — I build pipelines that work under real constraints.

8.48 CGPA
2K+ DSA Solved
99.2 JEE %ile
01 — About

Who I Am

I'm a third-year undergraduate at IIT Bhilai, studying Data Science & AI — one of India's most rigorous DS/AI programs. My work sits at the overlap of computer vision, NLP, and systems engineering, with real deployments for ISRO and competitive hackathon environments.

I operate at every level of the stack: from raw NumPy pipelines over Chandrayaan-2 XRF data, to training multimodal transformers, to shipping REST APIs with FastAPI. I care about results, not just methods.

My competitive programming habit isn't separate from my AI work — it sharpens the way I think about complexity, edge cases, and system design. 2000+ problems solved isn't a number — it's a problem-solving posture.

DSA Machine Learning Artificial Intelligence OS DBMS Computer Networks Big Data Analytics Probability & Statistics
// What I Bring to the Table
Research × Engineering fusion. I've processed real satellite data, trained multimodal models, and shipped working pipelines — not toy projects.
🎯
Competitive pressure experience. Inter IIT Tech Meet twice. ISRO-level problem statements. High-stakes, real deadlines.
🧠
Algorithmic depth. 2000+ DSA problems means I think about performance, edge cases, and optimization by default.
🔨
Full execution cycle. Idea → architecture → training → API → evaluation. I own the entire pipeline.
📐
Multi-domain range. Computer vision, NLP, RL, remote sensing, emotional AI — applied, not theoretical.
02 — Stack

Technical Arsenal

Languages
Python C++ C
AI / ML Frameworks
PyTorch TensorFlow YOLO-OBB scikit-learn Transformers
Data & Scientific
NumPy Pandas SciPy Astropy
Backend & Systems
FastAPI PySpark HDFS
Databases & Tools
MySQL MongoDB Git Linux QGIS
Core Domains
Computer Vision NLP Reinforcement Learning Remote Sensing Feature Engineering
03 — Projects

Selected Work

01 / INTER IIT TECH MEET 14.0 × ISRO
Vision42
Multimodal Vision-Language System for Satellite Imagery

Designed and built an end-to-end vision-language system capable of image captioning, Visual Question Answering, and text-driven object grounding — all on satellite data. The core challenge: rotated objects at arbitrary angles and extreme scale variability across orbital imagery. Addressed this with a hybrid pipeline coupling YOLO-OBB (Oriented Bounding Box) detection with a multimodal fusion architecture, served via FastAPI. Evaluated rigorously on IoU and BLEU-3 against GPU benchmarks under competition constraints.

6thRank / All IITs
BLEU-3NLP Metric
IoUDetection Metric
Python YOLO-OBB Multimodal DL FastAPI GPU Systems

View Code

#6 IIT Rank
02 / INTER IIT TECH MEET 13.0 × ISRO
Lunar Surface Mapping
Chandrayaan-2 XRF Data Processing Pipeline

Processed raw CLASS XRF spectrometer data from Chandrayaan-2 to generate high-resolution elemental composition maps of the lunar surface. Designed a custom clustering and spatial filtering pipeline to denoise orbital measurements, then leveraged PyTorch parallelization to cut processing time by 40%. Integrated QGIS and Astropy for geospatial analysis and astrometric calibration. Delivered production-quality lunar maps under competition deadlines.

40%Faster Processing
11thRank / All IITs
PyTorch NumPy SciPy Astropy QGIS Chandrayaan-2

View Code

#11 IIT Rank
03 / RESEARCH PROJECT
CauESC
Emotionally Intelligent Dialogue System with RL

Built a dialogue model that actually understands emotional context — not through keyword matching, but through COMET-based commonsense reasoning integrated with persona-conditioned generation. Introduced the Persona Attention Loop (PAL) architecture to maintain consistent persona across conversation turns. Trained in two stages: MLE on a pointer-generator network, then REINFORCE-based RL to optimize for non-differentiable dialogue quality metrics. Outperforms baselines across BLEU-4 and ROUGE-L.

3.92BLEU-4
16.91ROUGE-L
PALNovel Architecture
PyTorch Transformers REINFORCE RL COMET Pointer-Generator

View Code

PAL Novel Arch
04 / HACKATHON — THE FORGE × OPENAKE × GDG
StudySphere
Productivity Platform with Focus Efficiency Algorithm

Designed and shipped a full productivity platform during The Forge hackathon (Meraz 6.0). Core innovation: a custom Focus Efficiency Algorithm that quantifies user behavior patterns — beyond simple time tracking — to surface meaningful productivity insights. Built on React + Vite, deployed and demonstrated live. Secured 3rd position.

3rdHackathon Rank
React Vite Custom Algorithm

View Code

#3 Hackathon
04 — Achievements

Competitive Record

🏆
JEE Main — 99.20 Percentile
Top 0.8% nationally. Among ~1.2M candidates. Placed in the highest performance tier for India's most competitive engineering entrance.
🎯
JEE Advanced — AIR 6309
Cleared JEE Advanced with All India Rank 6309, qualifying for IIT admission — an exam with ~160K participants and a sub-10% selection rate.
🛰️
Inter IIT Tech Meet 14.0 — 6th Rank
ISRO problem statement on satellite vision-language AI. 6th across all IITs. Competed against the best technical minds in India under real-world space tech constraints.
🌕
Inter IIT Tech Meet 13.0 — 11th Rank
ISRO problem statement on Chandrayaan-2 data processing. 11th across all IITs. Processed real mission data under competitive deadlines.
IICPC 2025 — Finalist, Rank 1102
InterCollegiate Informatic and Competitive Programming Camp Private Limited. National finalist in one of India's premier competitive programming competitions. Top tier algorithmic problem-solving under time pressure.
🔨
The Forge Hackathon — 3rd Position
OpenLake × GDG at Meraz 6.0. 3rd place building StudySphere — a productivity platform with custom behavioral analytics algorithm, shipped in competition timeframe.
05 — Competitive Programming
2K+

Problems Solved

2000+ problems across Codeforces, CodeChef, LeetCode, and GeeksforGeeks. This isn't a metric — it's a mindset. Every problem is a lesson in edge-case awareness, time complexity intuition, and clean implementation under pressure. The same habits that make competitive programmers sharp make engineers reliable.

Codeforces Active Competitor
CodeChef Rated
LeetCode Interview-Ready
GeeksforGeeks Practice
IICPC 2025 Rank 1102 — Finalist
06 — Experience & Leadership

Experience

Campus Ambassador
Naukri Campus
2025 – Present
  • Drove hiring initiative visibility and competition participation across various colleges
  • Increased student engagement with placement resources and career competitions

Leadership & Activities

Mentor Coordinator
Student Mentorship Programme · IIT Bhilai
2025–26
  • Coordinated the mentorship structure for incoming students across batches
Event Coordinator
Meraz (4.0, 5.0, 6.0) — Annual Tech Fest
3 Editions
  • Organized events across 3 consecutive fest editions
  • Managed end-to-end coordination for informal-cultural-tech events
Core Member
Ingenuity Club · DSAI Club · Swara · Quizzotica
2024-26
  • Active in competitive programming club, DSAI Club, Music and Quizzing Club
  • Contributed to peer technical development and knowledge sharing

Let's Build
Something Real.

Open to research collaborations, internship opportunities, and high-impact roles in AI/ML engineering. If you're working on problems worth solving, I want to hear about them.

Open to internships and high-impact roles in AI/ML and software engineering, where I can work on real-world systems and challenging problems.