Akintayo Akinpelu

AKINPELU,AKINTAYOOLAOLUWA Mobile: +44 --https://github.com/Arkintea United Kingdom EDUCATION Sept. 2023 M. Sc. Artificial Intelligence and Data Science (Distinction) University of Hull, United Kingdom SKILLS Technical Skills: Python, SQL, Excel, MongoDB, OpenCV, NoSQL, Snowflake, NumPy, Pandas, ScikitLearn, TensorFlow, Keras, PyTorch, Kafka, Docker, PowerBI, Tableau, Git, DVC, Jax, MLflow, MLOps, Data modelling, Statistics, CI/CD, MLOps, Flask, Azure, AWS & GCP Cloud, Machine Learning, Deep Learning, Computer Vision, GANs, Natural Language Processing, LangChain, OpenAI API, Pinecone, Huggingface, GPT, Llama3, RAG, Generative AI, Large Language Models (LLMs), Prompt Engineering. Soft Skill: LEAN, Sigma, Agile, Scrum, Communication, Leadership, Time, risk and stakeholders’ management, Technical report writing, Critical reasoning, Technical research, Collaboration, Organizational skills and emotional intelligence. WORK EXPERIENCE Apr 2024 – Till date Sensor and Data Engineer University of Salford (Energy House 2.0) Achievement  Created robust data processing pipelines using Python. Handled data acquisition from numerous sensors, preprocessed for noise reduction, and integrated with Azure for real-time processing. Utilized APIs to streamline interactions with other software solutions.  Integrated sensor data with advanced analytics and visualization tools to extract actionable insights. Used Python for data analysis, uncovered patterns, and developed APIs for easy access to analytics results and visualization components.  Seamlessly integrated sensor data with enterprise systems used by house builders and heat pump suppliers. Utilized expertise in data acquisition and APIs to establish communication between sensor networks, Azure platforms, and stakeholders' systems. Sept 2023 – Mar 2024 Machine Learning Engineer iNeuron Intelligence Achievements  Designed and implemented a robust data pipeline for real-time IoT sensor fault detection using Kafka and PySpark. Ensured seamless data processing and fault detection in the sensor data stream, enhancing system reliability and minimizing downtime.  Deployed a machine learning model to predict premium insurance requirements based on customers' health conditions. Implemented GitHub Actions, Docker, Heroku, and MongoDB for model deployment and maintenance. Contributed to data-driven decision-making in the insurance sector, optimizing premium calculations.  Implemented a Convolutional Neural Network (CNN) deep learning classifier pipeline using Python, Keras, TensorFlow, and Docker. Ensured efficient image classification and model versioning, contributing to advancements in computer vision applications. Sept 2022 – Sep 2023 Graduate Student University of Hull, (Data Science, Artificial Intelligence and Modelling Lab, DAIM) Achievement  Developed AI tool for Lung cancer via image segmentation and detection from low-dose CT images using OpenCV, TensorFlow, Keras and Python.   Big data analysis of traffic accidents in the UK using SQL and Python Developed an AI tool for Covid-19 via image segmentation and classification using OpenCV, TensorFlow, Keras and Python. Oct 2020 – Sep 2022 Machine Learning Engineer IoT Africa Networks Achievements  Developed and deployed machine learning algorithms that predict equipment failures in real-time based on sensor data. By accurately forecasting maintenance needs, you significantly reduced downtime and maintenance costs for IoT devices, improving overall operational efficiency. I integrated the IoT data with Google Cloud Platform (GCP) Pub/Sub, BigQuery, ensuring data security and compliance by implementing encryption and access controls, to enhance scalability and reliability.  Designed IoT microservices & workflows, implemented demos, and POCs for clients, and provided technical support and training on Industrial IoT solutions with average resolution rate of 92% without escalation using NodeRed, Python, and Mosquito/MQTT.  Implemented anomaly detection systems using advanced machine learning techniques to identify irregularities in sensor data indicative of potential security breaches or equipment malfunctions. These systems enhanced the company's ability to detect and respond to cybersecurity threats and operational anomalies promptly.  Engineered machine learning models tailored for edge computing devices to enable real-time data analysis and decision-making at the edge of the IoT network. By reducing the need for constant data transmission to the cloud, you minimized latency, improved data privacy, and optimized bandwidth usage, enhancing the overall performance of IoT applications. Sept 2018 – Oct 2020 Data Scientist Powercube Responsibilities  Implementing predictive maintenance models to reduce downtime and increase the lifespan of critical equipment such as turbines, pumps, and generators. By analyzing historical sensor data, a data scientist can develop predictive models to anticipate equipment failures before they occur, allowing for timely maintenance interventions and minimizing costly downtime.  Developing algorithms and models to optimize energy generation processes, such as renewable energy forecasting or power plant scheduling. By leveraging machine learning techniques and historical data, data scientists can improve the accuracy of renewable energy forecasts, allowing energy companies to better plan their operations and reduce reliance on fossil fuels during peak renewable energy production periods.  Building models to forecast energy consumption patterns, enabling energy companies to efficiently allocate resources and manage energy supply. By analyzing historical consumption data along with external factors such as weather patterns and economic indicators, data scientists can develop accurate forecasts to help energy companies anticipate demand fluctuations and optimize their energy distribution networks.  Utilizing data-driven approaches to segment customers based on their energy usage patterns and preferences, enabling targeted marketing campaigns and personalized offerings. By applying machine learning algorithms to customer data, data scientists can identify distinct customer segments and tailor marketing strategies to better meet the needs and preferences of each segment, ultimately improving customer satisfaction and retention rates. PROJECTS    Developed a machine learning model for predicting the quality of wine using Python, Scikit-learn, Pandas, Numpy, Docker, Git/GitHub and AWS for deployment. Implemented MLOps for price prediction, using Python, Pandas, Numpy, Scikit-learn, Docker, DVC, MLflow, Airflow, Git, and Azure for deployment. Multiple Choice Question generator using Python, OpenAI API, Langchain, and streamlit  Designed and implemented a robust data pipeline for real-time IoT sensor fault detection using Kafka and PySpark. Ensured seamless data processing and fault detection in the sensor data stream, enhancing system reliability and minimizing downtime.  Built a conversational AI chatbot using natural language processing techniques to provide customer support and automate routine tasks. Developed deep learning models for medical image analysis tasks such as tumor detection, segmentation, and classification. Developed chat bots for websites using Python, Llama2 and Langchain   CERTIFICATIONS Feb 2024 iNeuron Generative AI Jun 2021 Project Management Specialization Coursera || Google Feb 2023 iNeuron Full-Stack Data Science Feb 2024 Data Engineering Bootcamp Grow Data Skills VOLUNTEERING Member, Drug Abuse and Quality Control Unit, National Youth Service Corps. Volunteer, Overcomers’ Christian Ministry Holiday School, Ayobo Lagos. Coordinator, Public Relations/Alumni, CASOR, Obafemi Awolowo University.