AI Engineer with 1+ years in AI/MLOps and Full Stack Development.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Faheela Shafi is a highly skilled AI & Automation Engineer with expertise in Python, C++, JavaScript, and frameworks like MERN and PyTorch. She has a strong background in Computer Vision, MediaPipe, and cloud platforms including AWS and Kubernetes. Her project experience includes developing real-time transport systems, hand gesture drawing applications with computer vision, language models, and head-detection systems. With a solid foundation in both AI/ML and full-stack development, she is adept at building scalable and intelligent solutions.
FAST-NUCES
BS · Computer Science
August 1, 2022 – Present
Microslush
AI & Automation Engineer
August 1, 2025 – June 1, 2026
India
Syszone AI Solutions
AI Developer Intern
June 1, 2025 – August 1, 2025
India
SensePC
Cloud & Backend Engineer
January 1, 2025 – March 1, 2025
India
Fiverr
Full Stack Developer
November 1, 2024 – December 1, 2024
India
SmartU Transport: Smart University Transport Management System
January 1, 2022 – Present
Built a real-time university transport platform using Flutter, FastAPI, PostgreSQL, and WebSockets; delivered GPS-powered shuttle tracking, live seat availability, RFID attendance automation, digital seat booking, and event-driven notification services. Developed a role-based transport operations dashboard supporting route management, fee and fine administration, occupancy analytics, transport usage reporting, and automated student communications for day scholars and hostelite commuters.
Hand Gesture Drawing App — Real-Time Computer Vision Drawing Interface
January 1, 2022 – Present
Built an in-browser drawing application using MediaPipe Hands and HTML Canvas, enabling real-time hand tracking with gesture-based interactions. Implemented pinch-to-draw, peace-sign color switching, index-finger erasing, and open-palm canvas reset; optimized gesture recognition for smooth, low-latency user experience.
Mini GPT Language Model — Character-Level Transformer (PyTorch)
January 1, 2022 – Present
Built a GPT-style autoregressive language model from scratch, implementing tokenization, self-attention, training loops, and text generation in PyTorch. Trained on curated Friends dialogue data to learn conversational patterns and generate context-aware character-level text sequences.
CrowdGuard — YOLOv8 Head-Detection & Overcrowding Alert
January 1, 2022 – Present
Fine-tuned YOLOv8 on JHU Crowd++ with FP16 training and INT8 quantization; Vercel-hosted dashboard with real-time threshold alerts for high-density environments.
Web Scraping Automation — Business Intelligence Data Extraction
January 1, 2022 – Present
Built Selenium-based automation pipelines to extract business listings from Google Maps; handled infinite scrolling, dynamic DOM rendering, stale elements, rate limiting, and anti-bot challenges for reliable large-scale data collection. Implemented automated data cleaning, validation, and structured export workflows for downstream analytics and business intelligence applications.
Spotify Listening Behavior Analysis — Data Analytics & Visualization
January 1, 2022 – Present
Performed exploratory data analysis (EDA) on Spotify listening datasets using Pandas, NumPy, and Matplotlib; analyzed user listening patterns, artist preferences, track popularity, and temporal consumption trends. Developed data visualizations and statistical summaries to uncover behavioral insights and support data-driven decision-making.
Masked Autoencoder (MAE) — Self-Supervised Vision Pre-training (PyTorch)
January 1, 2022 – Present
Built from scratch: 12-layer ViT encoder + 12-layer Transformer decoder trained on Tiny ImageNet with 75% patch masking, mixed-precision, and cosine LR scheduling; achieved PSNR 26.56 dB / SSIM 0.7277 and deployed on Hugging Face Spaces.
CaptionGen — Vision-to-Language (NLP + PyTorch)
January 1, 2022 – Present
End-to-end LSTM image-captioning pipeline on Flickr: tokenization, vocabulary engineering, feature extraction, and optimized batching in PyTorch.
Cultural Fit Analysis
The candidate's project portfolio is diverse, covering computer vision, NLP, data analytics, and full-stack development, indicating a broad interest and willingness to explore different technical domains. The academic and personal projects align well with an AI Engineer role, showcasing initiative and self-driven learning. The freelance experience also suggests an ability to deliver solutions independently. However, the professional experience is relatively short-term, which might indicate a need for more sustained team collaboration experience in a structured environment.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through complex project implementations (e.g., handling infinite scrolling in web scraping, optimizing gesture recognition). The project diversity suggests adaptability and a proactive learning attitude. Experience in building end-to-end systems indicates an understanding of operational requirements, though specific soft skills like teamwork or leadership are not explicitly detailed in the provided data.