Shuaib Iqbal

AI Engineer with 4+ years building production AI systems — spanning LLM-powered applications, RAG pipelines, agentic workflows, and the underlying machine learning models that power them — for enterprise clients across FMCG, IoT, and SaaS. Proven track record delivering Revenue Growth Management AI for global brands including EBM, PMI, RB-PK, and Unilever, cutting out-of-stock events by 20% and driving double-digit commercial growth. Skilled at taking projects from prompt design and retrieval pipelines through to scalable FastAPI/Django backends, owning delivery end-to-end alongside cross-functional product and engineering teams.

AI Engineer (Machine Learning Engineer) (2022-10 – Present)

• Built a natural-language-to-SQL tool (OpenAI API + LangChain) enabling plain-English querying over a 14M-row FMCG sales dataset, eliminating manual reporting cycles.
• Developed an AI-first Sales Intelligence Chat platform (OpenAI API + LangChain Agents + Streamlit) with multi-turn session memory, live sortable tables, and follow-up chaining for real-time FMCG insights.
• Delivered Revenue Growth Management AI pipelines for EBM, PMI, RB-PK, and Unilever — predictive selling models, route optimization, and White Space Identification algorithms driving double-digit commercial growth.
• Reduced out-of-stock events by 20% through time-windowed stockout forecasting models and automated alerting.
• Built multi-system integrations — REST APIs (FastAPI/Django) exposing ML insights to SaaS clients and ETL pipelines (Python, SQL) unifying POS and census data across millions of records — while owning delivery timelines across concurrent, Docker-containerized projects.

Associate Machine Learning Engineer (2022-05 – 2022-10)

• Improved HVAC forecasting accuracy by 25% by building and benchmarking ARIMA, LSTM, and XGBoost models on multi-sensor time-series data, selecting the best performer per building zone.
• Built real-time anomaly detection systems for IoT energy-wastage reduction, flagging abnormal consumption patterns and cutting manual monitoring effort for the facilities team.
• Designed time-series databases and backend services to ingest, clean, and store high-frequency sensor data from multiple IoT devices, ensuring reliable data for downstream forecasting models.
• Built Streamlit/Plotly dashboards giving non-technical stakeholders live visibility into forecasts and anomalies, and automated REST API reporting pipelines to remove manual report generation.
• Collaborated with hardware and backend engineers to validate sensor data quality and integrate ML outputs directly into the existing IoT platform.

ML Engineer — Internship (2022-02 – 2022-04)

• Built sales forecasting models (Prophet, LSTM, XGBoost) on historical transaction data, evaluated with MAE, RMSE, and R² to select the most reliable model per product category.
• Performed RFM (Recency, Frequency, Monetary) customer segmentation to identify high-value customer groups and support targeted sales strategies.
• Built interactive dashboards and backend reporting scripts to present forecasts and segmentation results to the team.

MS in Computer Engineering – NUST — National University of Sciences & Technology (2018 – 2021)

B.Sc. in Computer Systems Engineering – IUB — The Islamia University of Bahawalpur (2014 – 2018)