Muhammad Fahad Baig
Verified Expert in Engineering
Back-end Developer
Fahad is a back-end engineer with over two years of experience developing REST APIs, queueing architectures, and caching protocols for various applications. He specializes in Python, is well-versed in Flask, FastAPI, SQLAlchemy, PostgreSQL, MongoDB, RabbitMQ, and Redis, and has DevOps experience with Docker, AWS, and Azure. Fahad ensures modularity and extensibility while meeting functional and business requirements to deliver products that improve business processes and profitability.
Portfolio
Experience
Availability
Preferred Environment
Linux, Docker, Python 3, DataGrip, Visual Studio Code (VS Code), Agile Software Development, Windows Subsystem for Linux (WSL), FastAPI, Flask, Azure, Python
The most amazing...
...solution I've engineered and developed is a comprehensive AI-powered recruitment engine that parses and recommends resumes in two seconds against several jobs.
Work Experience
Senior Software Engineer
The Entertainer FZ
- Engineered a dynamic multi-tenant database system, reducing redundancy and enhancing performance.
- Integrated AWS Secrets Manager across the entire fleet of Python microservices for secured credentials management and ensuring PCI compliance.
- Worked on Amazon Personalize Services to offer merchant AI recommendations to end-users, leading to a 20% increase in user engagement and redemptions.
- Implemented a search-as-you-type feature as a global search to find hotels, offers, restaurants, and merchants across the entire application offerings.
- Developed RESTful APIs in Flask and FastAPI with AES encryption and JWT Authentication for improved data security, performance, and user experiences.
- Conducted code reviews, ensuring consistent, high-quality code across projects.
- Oversaw the code repositories, ensuring they met programming standards while guaranteeing the use of serializers, validations, and unit testing to improve processes.
Full-stack Developer
Blackwise, LLC
- Spearheaded the development of an MVP marketplace application for the black community, resulting in increased user engagement and a rise in subscriptions.
- Crafted the front-end application using React 18, Bootstrap, Framer Motion, jQuery, and GridJS, thus empowering users with advanced analytics, streamlined user management, and improved performance.
- Engineered the back-end application using FastAPI and Python, implementing JWT authentication, Pydantic schema validations, MinIO S3, Elasticsearch with NLP techniques, and MariaDB.
- Pioneered a web crawler and scraper to populate Elasticsearch indices, significantly reducing data retrieval times and enhancing content indexing efficiency. The system proactively indexed 1000+ websites, 1+ million links, and 500,000 images.
- Implemented multiple NLP and NER pipelines to power relevant searches and document/image tagging.
Back-end Python Engineer
Ricult
- Modernized and overhauled the previously deployed back-end stack to microservices and containers.
- Migrated the back end to FastAPI with Redis queueing and caching mechanisms, PostgreSQL warehousing, JSON Web Token (JWT) stateless authentication, and SQLAlchemy ORM.
- Led the design, architecture, and implementation of Ricult's new agent and farmer applications, alongside its development flow so other engineering teams could adhere to the workflows.
- Developed new back-end scheduling services using Azure Queue triggers and Azure Batch processing. Parallelized and improved deep learning models' inferences and performance on big data.
Artificial Intelligence Engineer
CureMD
- Developed SmartRecruit, an autonomous resume parsing and profiling pipeline that screens candidates and recommends them for jobs in under two seconds. Centralized CureMD's 60,000+ resumes with a span of 10+ years to its talent pool.
- Built an autonomous call-on-hold detection bot via a self-developed audio-to-speech recognition engine to transcribe calls and detect holding times. The waiting time was drastically reduced by 35%, while operator productivity increased by up to 50%.
- Led several AI and internal development teams across multiple projects, such as the data lakehouse, insurance claim extraction, medical billing, and interactive voice response (IVR) systems.
Assistant Artificial Intelligence Engineer
CureMD
- Developed an insurance card verification system using graph theory to restructure and extract key-value pair information from each card. The solution automated patient registration workflows at CureMD's partner hospitals and practitioners.
- Created a fax OCR engine to digitize and categorize patient medical records in the electronic health record (EHR) system, reducing manual labor costs by 30% and boosting CureMD sales.
- Provided mentorship, technical guidance, project charters, and development roadmaps.
Experience
SmartRecruit: Autonomous Resume Parsing and Grading
• The back end was designed using Flask and Docker and deployed on AWS ECR and Fargate. A load balancer was integrated to improve availability, and MongoDB was used as the database back end for NoSQL and unstructured data requirements.
• Built the framework of the system pipeline, from document parsing to information extraction, data normalization, candidate grading, and production deployment.
• Designed a robust PDF parser built on MuPDF that extracts key characteristics from PDF documents, such as text, fonts, indentations, objects, images, and lines.
• Created a heuristics-based prediction and probability model that takes in extracted features and performs heading segmentation and subsequent data population within each extracted heading.
• Trained the spaCy NER model (BERT) on a labeled corpus of education and experience to extract key entities such as organization, dates, roles, accreditations, and grades.
• Designed robust textual libraries using the FlashText algorithm to swiftly extract skills (50,000+ skills and categories), normalize institutions (3000+ institutions), and location data.
ID Card Identification and Data Extraction
The entire solution served as an Azure Function deployed to the cloud. An Android application was developed by the Avalon Team that called the back-end function to perform inferences. Solely I orchestrated, devised, and implemented the entire system pipeline, from identifying challenges, finding solutions, and realizing it to a production-grade product. Used OpenCV to identify rectangular card regions from raw images and then applied augmentation and vision routines to correct skew, reduce color variances, and make text prominent. And I also trained the end-to-end optical character recognition (OCR) pipeline using PaddleOCR.
The system achieved a remarkable 93% accuracy on text recognition and detection compared to 55% from Tesseract.
Calls Transcription and Hold Detection Bot
I evaluated several open-source automatic speech recognition (ASR) frameworks, such as Vosk, SPINE, OpenVINO, and NeMo, for WER analysis on internal insurance voice calls. Then I designed and implemented a robust messaging-based queuing protocol system on top of RabbitMQ to initiate calls, run transcriptions, detect hold times, cancel calls, and handle interactive voice response (IVR) to process up to 40 calls concurrently.
Blackwise Search Engine
https://app.blackwise.coSkillset
Languages
Python, Python 3, SQL, CSS, HTML, JavaScript, CSS3
Frameworks
Flask, Django, Selenium, JSON Web Tokens (JWT), Django REST Framework, OAuth 2, Alembic
Storage
JSON, PostgreSQL, Amazon S3 (AWS S3), MongoDB, MySQL, MariaDB, Redis, Redis Cache, Elasticsearch, Couchbase
Libraries/APIs
SQLAlchemy, REST APIs, Python API, Flask-RESTful, Pydantic, Pandas, NumPy, OpenCV, React, Redis Queue, Python-rq, Beautiful Soup, TensorFlow, Shapely, Python Asyncio, SpaCy, Pika, Sockets, Amazon EC2 API
Tools
RabbitMQ, Git, PyCharm, Celery, Docker Compose, You Only Look Once (YOLO), NGINX, AWS Fargate, DataGrip, Amazon Elastic Container Registry (ECR), Certbot, Kibana
Paradigms
Agile Software Development, REST, Scrum, DevOps, Object-oriented Programming (OOP), Automation, Asynchronous Programming, Database Design, Functional Programming
Platforms
Docker, Amazon EC2, Linux, Azure, Amazon Web Services (AWS), Azure Functions
Other
FastAPI, Back-end, Poetry, Data Analysis, Azure Virtual Machines, Natural Language Processing (NLP), OCR, Artificial Intelligence (AI), Gunicorn, PaddleOCR, Tesseract, Windows Subsystem for Linux (WSL), Data Scraping, APIs, Web Scraping, Python Dataclasses, GPT, Generative Pre-trained Transformers (GPT), WebSockets, Back-end Development, RESTful Services, Containerization, Leadership, Scalability, Technical Leadership, Cloudflare, Torch, GeoJSON, Automatic Speech Recognition (ASR), AWS Auto Scaling, Computer Vision, Speech Recognition, Search Engine Development, Search Engines, Scraping, CI/CD Pipelines, Database Optimization, Performance Optimization
Education
Bachelor's Degree in Electrical Engineering
National University of Sciences and Technology - Islamabad, Pakistan
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring