Data Scientist Machine Learning

Saad Siddiqui

Senior Data Scientist Lead Data Scientist Applied ML Engineer

+1-586-***-**** WASHINGTON, DC linkedin.com/in/sms-ned16 10/28/1988 PROFILE

Accomplished and highly innovative Data Scientist and Machine Learning Engineer with over 10 years of diverse experience in building and deploying cutting-edge AI solutions across telecommunications, healthcare, and finance sectors. Adept at leading and mentoring teams to design, develop, and implement advanced machine learning algorithms and AI models that transform businesses. Proficient in orchestrating data-driven strategies to solve the most complex problems with Python, R, STAN, and deep learning techniques. Skilled in building robust end-to- end AI solutions, from data pipelines to model deployment, driving scalable business impact. Demonstrated leadership in project management, AI-driven decision-making, and cross-functional collaboration, optimizing performance and revenue across high-profile clients and organizations. SKILLS

Languages & Frameworks:

Python, R, SQL, C++, Java, MATLAB, Bash, Shell

Scripting, JavaScript (Bootstrap, CSS)

Data Engineering:

ETL Pipelines, Data Cleaning, Feature Engineering, Time-Series Analysis

Cloud & Deployment:

AWS, Google Cloud, Git, GitHub, CI/CD pipelines,

Docker, Kubernetes, Serverless Computing

Data Visualization:

Power BI, Tableau, Matplotlib, Seaborn

Data Science & ML Tools:

TensorFlow, Keras, Scikit-learn, LightGBM, XGBoost, STAN, Pandas, NumPy, Seaborn, Matplotlib, Deep

Learning, Reinforcement Learning, Bayesian

Inference, Time-Series Forecasting, NLP, Image

Recognition, Predictive Analytics

Statistical Modeling:

Bayesian Statistics, Predictive Analytics, A/B Testing, Regression, Classification, Performance Monitoring Database:

MySQL, Database Queries, SQL

Industry-Specific Expertise:

Healthcare, Insurance, Supply Chain, E-Commerce

PROFESSIONAL EXPERIENCE

Afiniti

Lead Data Scientist

09/2022 – present Washington, DC

•Designed and deployed a RAG-based ChatGPT system with semantic search, leveraging Pinecone for scalable vector-based document retrieval.

•Enhanced query accuracy through advanced metadata filtering and LLM-based reranking, improving relevance for the Cloud Operations Platform Team.

•Developed a fully automated faceless video generation pipeline using agentic AI workflows to streamline marketing content production.

•Engineered an AI-powered call analytics platform for retail, applying speech-to-text and NLP to extract actionable insights from customer conversations.

•Integrated sentiment analysis, intent detection, and automated reporting to enhance customer experience and operational strategy.

•Built and maintained robust, end-to-end data pipelines supporting seamless data ingestion, transformation, and model deployment at scale.

•Facilitated stakeholder workshops to align AI initiatives with underwriting and product strategies, driving measurable business outcomes.

•Mentored cross-functional teams on Agile practices, fostering iterative development, faster delivery, and continuous process improvement.

Afiniti

Senior Data Scientist – Applied AI

02/2022 – 09/2022 Karachi, Pakistan

•Developed price elasticity and retention models for auto and property insurance to quantify premium sensitivity and predict policy renewal behavior.

•Leveraged historical policy, claims, and pricing data to optimize underwriting strategies and improve customer lifetime value.

•Led the development of a credit risk assessment model using ensemble machine learning techniques,

•improving default prediction accuracy by 18% and reducing loan loss provisions by $15M annually.

•Designed and implemented predictive models such as Bankruptcy Prediction for the Order to Cash team,

•resulting in improved risk management and reduced financial discrepancies, achieving a 10% reduction in bad debt ratio.

•Implemented an NLP-based email classification system using word embeddings to categorize service requests and improve customer support efficiency.

•Led the development of an Unauthorised Utilisation Detection System for Visi Coolers using computer vision and OpenCV techniques.

Afiniti

Data Scientist – AI Production

10/2021 – 01/2022 Karachi, Pakistan

•Drove a £500K/month increase in revenue through enhancements in downgrade models for Sky UK, optimizing customer retention and improving model scalability.

•Led the transition to Afiniti V6 architecture, ensuring the migration of all production models and processes with zero downtime, streamlining deployment pipelines and reducing 50% in deployment time.

•Developed predictive models for interim performance reporting, contributing to more efficient resource allocation and performance tuning in customer care strategies. Afiniti

Junior Data Scientist – AI Production

08/2020 – 09/2021 Karachi, Pakistan

•Delivered 14% improvement in customer care revenue and £200K monthly incremental revenue by building models that optimized agent-caller pairing in contact centers.

•Designed and implemented advanced feature engineering techniques for time-series data, leveraging telephony and CRM data to predict customer behavior with high accuracy.

•Automated reporting and diagnostic frameworks, enabling more effective tracking of model performance and contributing to the success of 3 new model deployments across Sky UK and Virgin Media. Detectovid

Data Engineer

06/2020 – 08/2020 Karachi, Pakistan

•Spearheaded development of advanced analytics models, including Disengagement and Attrition Risk models to predict workforce churn.

•Developed an AI-powered resume scoring tool to evaluate candidate profiles based on job relevance, skills match, and experience using NLP techniques.

•Enabled automated shortlisting by integrating with applicant tracking systems, improving recruiter efficiency and hiring quality.

•Achieved 15% reduction in Days Sales Outstanding (DSO) through development and implementation of scalable intelligent collection engine for UK, Belgium, and Canada, optimizing operational efficiency and accuracy in Order to Cash processes.

Virufy

Machine Learning Engineer Remote

04/2020 – 05/2020

•Designed and deployed multiple recommendation systems, including historical behavior-based, repeated offer detection, and NLP-driven content recommendations.

•Built profiling models using digital activity, purchase intent, and purchasing power to tailor personalized offers for different customer segments.

•Implemented using Python, Flask, AWS, and Snowflake, enabling scalable delivery of real-time recommendations across channels.

•Conducted extensive feature engineering on large datasets to ensure the accuracy of models, reducing prediction errors by 25%.

Neurocomputation Lab - NCAI

Machine Learning Intern

12/2019 – 03/2020 Karachi, Pakistan

•Managed and supported applications across data engineering, analytics, and visualization, enabling strategic workforce insights and decision-making.

•Acted as SME for FMCG analytics, collaborating across finance and supply chain teams.

•Conducted customer sentiment analysis and topic modeling from feedback using NLP, improving feature prioritization.

•Designed and implemented time-series forecasting models using XGBoost and scikit-learn to predict cashflows for strategic financial planning.

•Improved forecast accuracy and planning efficiency, enabling better budget allocation and liquidity management.

K-Electric

Electrical Engineering Intern

08/2019 – 09/2019 Karachi, Pakistan

•Analyzed fault data and identified common issues in coastal substations and aerial bundled cables, contributing to operational improvements.

•Gained hands-on experience with preventive maintenance procedures for various electrical infrastructure systems.

Lucky Cement Limited

Electrical Engineering Intern

05/2019 – 06/2019 Karachi, Pakistan

Freelance

Junior Machine Learning Engineer

12/2015 – 04/2019

•Delivered tailored AI-driven solutions for clients across telecommunications, healthcare, and finance, providing value through predictive models and data analytics.

•Developed and deployed deep learning models for complex tasks such as image recognition, natural language processing (NLP), and fraud detection, resulting in measurable business outcomes.

•Collaborated with clients to design end-to-end AI solutions for customer segmentation, sales forecasting, and predictive maintenance, optimizing business processes and performance. EDUCATION

NED University of Engineering and Technology

BE Electrical Engineering

2016 – 2020

•Grade: CGPA 3.936 Class Rank - Top 5% With DistinctionGrade: CGPA 3.936 Class Rank - Top 5% With Distinction

•Activities and societies: NED Artificial Intelligence Club Georgia Institute of Technology

Master of Science - MS, Computer Science

2023 – 2025

•Grade: 3.9 / 4.0Grade: 3.9 / 4.0

•Specialization: Machine Learning

Contact this candidate