M.Y. Hussain

> ./init --profile yaser ··· ok

AI / ML Graduate

Specialising in applied machine learning, deep learning, and intelligent systems.

// 01 · about

About

I am Mohammad Yaser Hussain, a fresh AI and Machine Learning graduate from Jayaprakash Narayan College of Engineering, affiliated to JNTU, Hyderabad.

I work across the full range of AI engineering, from systems-level thinking and performance optimization to designing intelligent pipelines and applied machine learning. I am not attached to any one approach or tool. I follow the problem and figure out what it actually needs.

Building software that works in the real world matters to me more than building software that looks good in a demo. That means caring about performance, reliability and the experience of whoever ends up using it. I am also a published researcher with peer-reviewed work in machine learning applied to real world market analysis.

0
Projects
0
Published Paper
0
Certifications
May '26
Graduated
// 02 · projects

Project Experience

windows desktop · multimodal ai assistant

F.R.I.D.A.Y: On-Device Multimodal AI with Autonomous System Control

source ↗
  • Windows desktop AI assistant: a local Qwen2.5-VL LLM handles text and vision reasoning, backed by a 4-block CNN (trained from scratch in PyTorch, BatchNorm + dropout) as an offline vision fallback; STT via faster-whisper runs fully local, and TTS tries Edge TTS first, falling back to Kokoro-82M and then Windows SAPI so speech still works offline
  • Hybrid ML/DL intent pipeline: TF-IDF + LinearSVC (scikit-learn) handles near-instant classification and DistilBERT (ONNX Runtime) with dynamic CPU/GPU provider selection handles complex queries, both routed by a heuristic complexity score, plus a rule-based short-circuit that skips inference entirely for small talk
  • Concurrent PyQt6 application decoupling DL inference in an isolated worker process, wake-word detection via openWakeWord, and OS system control with structured JSONL telemetry
  • SQLite conversation history with an optional ChromaDB + sentence-transformers semantic-memory layer (feature-flagged, deterministic fallback embedder when disabled) and spaCy NLP for entity extraction, alongside real-time audio waveform and hardware telemetry panels
Python / PyQt6Qwen2.5-VLDistilBERT / ONNXscikit-learn spaCyfaster-whisper openWakeWordChromaDBSQLite

android · multi-engine on-device ai

QuantLM: Multi-Engine On-Device AI Inference App (Android)

play store ↗
  • Privacy-first Android app for chatting with a curated library of Qwen, Phi, SmolLM/SmolVLM, and Gemma models entirely offline, with text, vision, and audio support
  • Multi-engine inference layer routing three model formats (GGUF, MediaPipe .task, and LiteRT-LM .litertlm) through dedicated llama.cpp, MediaPipe, and LiteRT-LM engines behind one chat interface
  • Custom C++17/CMake JNI bridge builds llama.cpp with a Vulkan GPU backend and seven HWCAP-scored ggml CPU variants selected at runtime, gated by a device capability probe and RAM-aware load warnings that guard against freezes on low-memory hardware
  • Clean Architecture with Dagger Hilt and Kotlin Coroutines; a WorkManager-backed downloader handles background model downloads and hot-swapping multi-gigabyte files while Room persists chat history without blocking the UI
KotlinC++17 / JNIllama.cppMediaPipeLiteRT-LM Dagger HiltJetpack ComposeWorkManagerRoom

applied ml · agentic financial analysis

SEC Insider Trading Analysis: Multi-Agent System

source ↗
  • Four-stage CrewAI Flow (@start/@listen) pipelining SEC EDGAR filing retrieval, insider-transaction analysis, and week-over-week historical comparison through custom Pydantic-typed CrewAI tools, with a dedicated report-writing agent synthesizing the final output
  • Dual-LLM design: a local Ollama model (Llama 3.2 by default) drafts the report, then Google Gemini 2.0 Flash independently cross-checks it against the raw transaction data and silently corrects arithmetic, attribution, and count errors before it ships
  • Real-time Form 4 and 8-K ingestion via ATOM feeds with Pydantic for type-safe tool schemas and BeautifulSoup for XML parsing, plus retry-with-exponential-backoff and data-validation guardrails at every step that accumulate errors instead of aborting the run
PythonCrewAIOllama PydanticBeautifulSoup Gemini 2.0 FlashSEC EDGAR
// 03 · skills

Technical Skills

Machine Learning & Deep Learning

PyTorch TensorFlow scikit-learn HuggingFace Transformers ONNX / ONNXRuntime sentence-transformers

NLP, Speech & Vision

spaCy faster-whisper OpenWakeWord OpenCV MediaPipe

Generative AI & Agents

llama.cpp / llama-cpp-python LiteRT-LM CrewAI Google Gemini API Ollama ChromaDB On-device LLM (Qwen · Phi · SmolLM · Gemma)

Android & Edge Deployment

Jetpack Compose Android NDK / CMake Kotlin Coroutines Dagger Hilt Room Database WorkManager Vulkan GPU

Languages & Tools

Python Kotlin C++ / C++17 Pandas / NumPy Matplotlib / Seaborn Pydantic PyQt6 BeautifulSoup4
// 04 · github

GitHub Statistics

Repositories
Total Stars
Total Commits
Followers
Contributions
// 05 · research

Publications

Peer-Reviewed · Journal Article · 2024

Enlightening Paths: Python's Vision into the Electric Vehicle Market

Hussain, M. Y. · Abrar, M. A. · Aiman, M. I. · Srinivas, T. A. S.

Journal of Communication Engineering & VLSI Design, Vol. 2(2), pp. 28–35

View on ResearchGate ↗
View paper
// 06 · education

Education & Certifications

Degree

Bachelor of Technology

Jayaprakash Narayan College of Engineering
Affiliated to JNTU, Hyderabad

AI & Machine Learning Graduated May 2026

Certifications & Training

Google Gemini Certification

Google

Oct 2025 View

Artificial Intelligence Internship

AICTE · Edunet Foundation · IBM SkillsBuild

Nov–Dec 2024 View

Machine Learning for All

University of London · Coursera

Oct 2024 View

Computer Vision 101

Infosys Springboard

Aug 2024 View