Asad Abbas
Verified Expert in Engineering
Data Scientist and Machine Learning Developer
Lahore City, Punjab, Pakistan
Toptal member since April 8, 2025
Asad is a principal data scientist with 8+ years of experience developing and deploying machine learning solutions for global enterprises. His expertise in AI-driven projects, including AI interview summarization and developing LLM-based AI chatbots, showcases his ability to lead complex initiatives. A Databricks-certified professional, Asad is proficient in building end-to-end ML solutions and excels in working with LLMs, classical ML, and time-series forecasting technologies.
Portfolio
Experience
- Machine Learning - 8 years
- Data Science - 8 years
- Python - 8 years
- SQL - 6 years
- Time Series Forecasting - 4 years
- Databricks - 4 years
- FastAPI - 2 years
- Generative Artificial Intelligence (GenAI) - 2 years
Availability
Preferred Environment
Windows, Python
The most amazing...
...project I've worked on is an AI interview system deployed on AWS. It summarizes interview transcripts and rates candidates on job attributes.
Work Experience
Principal Machine Learning Engineer
Confiz
- Developed an AI-powered loyalty program solution that combined ML-based customer segmentation with a GPT-4o RAG chatbot to help campaign managers understand customer segments for hyper-personalized marketing, with the solution deployed on Azure.
- Created an AI interview system that analyzes interview transcripts to summarize conversations, evaluate candidates on job-specific attributes, assess answer quality, and provide live interview assistance, all deployed in AWS for production use.
- Led the development of a Generative AI text summarization tool that processed proprietary documents using GPT-3.5 and GPT-4, executing structured prompts via LangChain and Pydantic-based JSON parsing, along with a supporting Flask back-end service.
- Built a multivariate time series forecasting application in PySpark that featured config management with Dynaconf, CI/CD via Jenkins, an integrated model selection pipeline comparing Prophet and SARIMAX models, and migration from Spark 2.4 to 3.1.
Machine Learning Engineer
Cialfo
- Developed a machine learning model using LightGBM to predict whether students would apply to 10+ programs across multiple universities, incorporating student attributes, university data, and platform interaction features.
- Created a personalized search model using LightGBM, which displayed university search results by leveraging embeddings for search terms, student demographics, university attributes, and temporal data with AWS-Airflow pipelines.
- Built a machine learning model to help universities predict student application likelihood by month, incorporating temporal and non-temporal features about students and universities, with training and prediction pipelines in MWAA and AWS.
Data Scientist
Systems limited
- Developed and deployed a multivariate time series sales forecasting application for Estee Lauder that incorporated external regressors, statistical evaluation metrics, and optimized ML pipelines with parallel execution capabilities.
- Built an IoT application for Regeneron that established connections with facility devices using HTTP and SNMP protocols, extracted real-time data, and created custom visualization widgets on an IoT platform alongside a web application.
- Designed a pricing engine for VavaCars that predicted purchasing offers for used cars by analyzing data sources from Turkey and Pakistan, extracting price-impacting features, and generating automated mapping using fuzzy matching.
Data Scientist
Afiniti
- Developed predictive models using different regression techniques and innovative ideas to optimize the call center interactions between customers and agents.
- Analyzed 3rd-party data on Vodafone to filter valuable variables by measuring variations in conversion rates, call volumes, and time-dependent correlations.
- Examined incoming data sources to measure their quality for optimization by running time-series, random, and K-fold validations.
Experience
AI Interview System
Education
Bachelor's Degree in Electronics Engineering
GIK Institute of Engineering Sciences and Technology - Swabi, Pakistan
Certifications
Databricks Certified Machine Learning Professional
Databricks
Skills
Libraries/APIs
PySpark, Pydantic
Tools
AWS CLI, Jenkins
Languages
Python, SQL, Snowflake
Platforms
Databricks, Amazon Web Services (AWS), Azure, Windows
Frameworks
Flask, LightGBM
Storage
Redis, JSON
Other
Machine Learning, Data Science, Time Series Forecasting, FastAPI, Generative Artificial Intelligence (GenAI), Retrieval-augmented Generation (RAG), Large Language Models (LLMs), Data Structures, Electronics Engineering, Generative Pre-trained Transformer 4 (GPT-4), Generative Pre-trained Transformer 3 (GPT-3), Generative Pre-trained Transformers (GPT), LangChain, Artificial Intelligence (AI), Customer Segmentation, Chatbots, AI Chatbots, CI/CD Pipelines, Amazon Managed Workflows for Apache Airflow (MWAA), ML Pipelines, Internet of Things (IoT), Web Applications, Predictive Modeling, SNMP, HTTP
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