Open to AI/ML opportunities

Aryan Singh
AI/ML Engineer

B.Tech CSE graduate with research experience at ISRO and IIT Ropar. I build embedded ML systems, speech models, and computer vision pipelines — turning complex problems into deployable solutions.

Speech & Audio ML Computer Vision Embedded AI Deep Learning Python
View my work Get in touch
About
By the numbers
25%
Accuracy gain over Vosk & Picovoice on TRISHNA satellite wake-word model
Top 0.3%
Flipkart GRID 6.0 — out of 100,000+ participants nationwide
90%+
Model accuracy across 3 domains at IIT Ropar
2x
User engagement improvement via predictive ML models at CodeClause
5,000+
Labeled images in custom quality control dataset
95%
OCR accuracy on assistive reading device built on Raspberry Pi

I'm a Computer Science graduate from Mohanlal Sukhadia University, Udaipur. My interest is in the intersection of machine learning and real-world deployment — building systems that work under constraints, not just in notebooks. I spent three months at ISRO's Space Applications Centre building a mission-critical speech model for satellite operations, and two months at IIT Ropar researching applied AI across vision and NLP domains.

Experience
Where I've worked
ISRO — Space Applications Centre, Ahmedabad
Research Scholar
Jan 2025 – Apr 2025
  • Engineered a CNN + MFCC-based wake-word detection model for the TRISHNA satellite's voice command system, achieving 25% higher accuracy than Vosk and Picovoice at 80%+ ambient noise levels.
  • Applied noise augmentation techniques (white noise, time shifting) to overcome a small dataset constraint, improving model robustness under satellite payload conditions.
  • Validated real-time inference on resource-constrained embedded hardware; achieved sub-200ms response latency with fault-tolerant activation logic.
  • Collaborated with 5 ISRO scientists and engineers to integrate the model into the satellite's control system, improving overall voice-command efficiency by 20%.
CNNMFCCTensorFlowEmbedded MLData Augmentation
IIT Ropar — CSE Dept. / iHub-AWaDH
Research Intern · AI Vicharaṇā Shālā Program
May 2024 – Jul 2024
  • Researched and implemented AI systems across computer vision, cryptography, and recommendation domains using TensorFlow, OpenCV, and Keras; trained models achieving 90%+ accuracy across all task categories.
  • Delivered 3 functional prototypes — object detection, image steganography, and a neural recommendation engine — for academic review at IIT Ropar.
OpenCVKerasObject DetectionSteganographyRecommendation Systems
CodeClause Pvt. Ltd., Udaipur
Data Science Intern
Dec 2023 – Jan 2024
  • Applied K-means clustering on real user behavioural data to personalise push notification content and timing, doubling user engagement (100% increase) over a 4-week A/B test cycle.
K-meansScikit-learnData MiningA/B Testing
Projects
Things I've built
🛰
TRISHNA Satellite Wake-Word System
CNN-based binary wake-word classifier for ISRO's TRISHNA satellite voice command interface. MFCC feature extraction + noise augmentation pipeline. Outperformed Vosk and Picovoice by 25% in high-noise environments.
Python TensorFlow MFCC Embedded
View on GitHub →
📦
Smart Vision Quality Control
Automated computer vision pipeline for product inspection — classifies 20+ product types and evaluates freshness/count for 30+ fruit and vegetable categories from a 5,000+ image dataset. Reduced manual inspection effort by 40%.
YOLOv8 Roboflow Python OpenCV
View on GitHub →
📖
OCR Speaking Lamp
Raspberry Pi-powered accessibility device that reads printed text aloud in real time. Tesseract OCR + pyttsx3 text-to-speech pipeline. Achieves 95% OCR accuracy — designed for visually impaired users.
Raspberry Pi Tesseract OCR Python pyttsx3
View on GitHub →
+
More coming soon
Currently building a real-time audio transcription and speaker diarization tool using Whisper + PyAnnote. Deploying on HuggingFace Spaces.
Whisper PyAnnote HuggingFace
Skills
What I work with
Languages
Python C++ Java SQL JavaScript
ML / AI Frameworks
PyTorch TensorFlow Scikit-learn OpenCV Keras
Specialisations
Speech Processing Computer Vision NLP Embedded ML OCR
Tools & Platforms
Git / GitHub Raspberry Pi Roboflow Google Colab MySQL
Recognition
Achievements & certifications
🏆
Top 0.3% — Flipkart GRID 6.0 (100,000+ participants)
Software Development, Information Security & Robotics tracks — Certificate of Merit, Flipkart
🧪
Letter of Recommendation — ISRO Division Head
Issued by Head of PCSVD, Space Applications Centre for outstanding research on the TRISHNA satellite project
🥇
HackerRank Gold Medal — Python & SQL
Certified outstanding performance in Python (Basic) and SQL (Basic) skill assessments
💼
Graduate Engineer Trainee — Secure Meters Ltd.
Highest placement offer from the 2025 graduating batch at IET, MLSU Udaipur
🎓
IIT Ropar — AI Vicharaṇā Shālā Completion Certificate
2-month residential hands-on AI program, CSE Department, IIT Ropar × iHub-AWaDH

Let's work together

I'm currently open to AI/ML engineering roles, research positions, and collaborative projects. Feel free to reach out.

aryansingh4653@gmail.com LinkedIn GitHub