Christopher M.

As Chief Technology Officer at Apex Health for Life, I lead the architecture, engineering, and product development of a Human Digital Twin platform that delivers personalized, adaptive health interventions through a mobile application with wearable integration. Our platform is built on the premise that physical health, genomic, transcriptomic health, emotional wellbeing, and behavioral patterns are deeply interconnected, and that a truly intelligent health system must model those connections in real time, not treat them as isolated data streams. I own the end-to-end technical vision from research through deployment, translating peer-reviewed concepts in multimodal sensing, graph-based modeling, and reinforcement learning into a production-grade consumer health product. My focus is on building systems that don't just score or track....they reason, adapt, and learn from each user interaction to deliver increasingly personalized guidance over time.

Helped a team of AI engineers developing and implementing advanced machine learning models for a mobile health coach application utilizing conversational AI, and large language models built from the ground up and programmed with custom engineering and custom applications including utilizing RAG knowledge base, fine tuning and "agentic AI" concepts. Including building custom neural network transformers utilizing contemporary and breakthrough innovation and research. Oversaw the development of image processing and analysis capabilities "Food Buddy", including food image recognition and nutritional data extraction, also voice to voice conversational interface component, blood analysis panel utilizing AI and patient blood work. Implemented query optimization techniques in vector databases (RAG) to improve system performance and responsiveness. (Qadrant, Milvus). Managed the development of content management systems, including onboarding processes and audio file conversion tools. (Deep Gram, Eleven Labs). Created POC's for "Patent Buddy" component to help legal team query US patent data using natural language. Collaborated with cross-functional (front-end, back-end, web design, database) teams to integrate AI solutions across the platform. Implemented data pipelines and preprocessing workflows to handle large-scale datasets efficiently Conducted testing and performance analysis to continuously improve LLM model accuracy and efficiency. Mentored junior team members and provided technical guidance on AI and machine learning best practices. Coordinated with product management to align AI development with business objectives.

Through Python programming, automated and streamlined analysis tasks for wastewater treatment monitoring and report generation for the Hawaiian State Laboratories DPEI. **Predictive Modeling and Machine Learning: Applied machine learning algorithms for predictive modeling of COVID-19 spread and detection of Candida species in wastewater; improved disease surveillance and public health response. **Bioinformatics and Environmental Health: Conducted bioinformatic analysis on wastewater samples to detect and monitor the presence of pathogens, providing critical data for public health decisions and strategies.

Contract-Machine learning engineer and Bioinformatics Scientist at prestigious biomedical company for oncology research. Python application development for machines learning programs for exploratory and data analysis. Build NGS pipelines and utilize many different programs and applications for RNA Seq and WES workflows using Cromwell workflow manager. Work extensively with Docker containers, WDL files, JSON files. Utilize cloud computing platforms like AWS, and Azure to perform analysis and pipeline data engineering functions with Synapse, Blob storage, EC2 instances, Athena, AWS Glue, Cosmo DB. Utilize Natural Language programs and API's to perform entity extraction on medical documentation, and diagnostic reports. Use clustering programs and classification programs like decision trees to classify disease potential with VCF file analysis and variant calling. Preprocess, normalize and standardize data to pipeline it into NLP transformer programs like 'BERT'.

At NCI Information Systems, I steer efforts to enhance NLP models performance and “persona” based AI platform using Sentence BERT/Top2Vec/RoBERTa based language embedding technologies. As a Sr. Artificial Intelligence Engineer, I use Python and R to deliver top clustering NLP model into production. Leveraging my key expertise, I supervised all activities related to software development life cycle and quality assurance testing, methodologies, and tools. Demonstrating my broad scope of knowledge, I design frameworks such as MLlib, scikit-learn, TensorFlow, and Keras. Furthermore, I orchestrate automated Kubernetes workflows for deployment by maintaining cloud computing AWS, Azure, vCenter/VMware, and platforms. I evaluate and assess proposal content and confirm cross volume consistency. Some of my key contributions are as follow: ☛ Significantly increased knowledge management availability by 30% and relevance of searches by 90% as well as reduced the average time to search for a solution up to 20% by implementing “Enterprise Brain” NLP program/algorithm for the General Services Administration. ☛ Used topic modeling/NLP programs to complete “Body of Knowledge” inhouse project allowing people to search through all existing information in ‘SharePoint” database and answer own questions. ☛ Utilized Kubernetes cluster to reprogram company’s flagship NLP topic model cluster algorithms - "Enterprise Brain" that helped in boosting algorithms storage, preprocessing and clustering capabilities. ☛ Designed custom NLP models with chat personas that aided in evaluating, assessing, clustering, and creating topic models from documents and large text data. ☛ Received training for back-end brain machine learning applications for NLP, transformers technology such as ‘BERT’, RoBERTa, Universal Sentence Encoder in Python, R, Linux/Ubuntu. ☛ Delivered support to the operations team in understanding technical solutions and commitments for performance.

As a Computational Biologist, I implemented best practices to effectively manage complex biomedical data through modern computational approaches. Utilizing my key expertise, I oversaw exploratory research on single cell analysis and bulk RNA analysis to examine different levels of gene expression. Furthermore, I used Next Gen Sequence technologies (NGS) and introduced single cell analysis pipelines to develop biomarkers for drug therapeutics. Leveraging technical skills, I adeptly utilized python, Linux, UNIX, and IGV gene analysis software for RNA single cell data processing and virus and human genes analysis with program algorithms. Some of my key contributions are as follow: ☛ Developed cell analysis pipelines and uploaded on proprietary software “Single Cell Explorer Analysis” database by using python programming, including Linux and UNIX on HPC clusters, AWS cloud computing software, and EC2 virtual machines for efficient data storage for department lab personnel. ☛ Trained lab scientist on bioinformatics tools, statistical methods, and High-Performance Computing in Linux to accelerate knowledge. ☛ Implemented artificial intelligence programs/scripts using python programming with TensorFlow, and Python libraries like “Scanpy” for single cell data analysis. ☛ Scrutinized, visualized, and clustered an analysis using Linux scripting and python programming and uploaded to inhouse single cell visualization explorer software for single cell analysis experiments on metabolic diseases. ☛ Designed web application databases with Django, JavaScript, Nginx, and AWS software platforms to arrange effective internal training programs and survey questionnaires for colleagues. ☛ Enhanced single cell data analysis by expertly using different clustering algorithms and dimensionality reduction methods like (UMAP, T-SNE), resulting in identified and isolated biomarkers of specific cells to find treatments.

Relevant Courses: • Database architecture design using MySQL, Microsoft Server. As well as working with IBM platforms and big data applications like Hadoop. Oracle, Open Source. • Machine learning using Python, and libraries “pyTorch”, sciKitLearn, tensorflow to develop deep artificial neural networks for problem solving. • Basic cloud database architecture. (Open-Stack, Cloudera) • Probability theory and matrix theory and it's applications Data Science/Deep Learning. • Advanced Python programming skills with application to data science. • Distributed database design, utilizing Hadoop and other big data management tools • Software project management including “Six Sigma” Quality Management • Completed Udemy and Coursera course work in machine learning, data science, and deep learning • Natural Language Processing, digital image recognition(CNN’s) training • Microbiology with lab • Database design for Biological Research

 Gather, analyze and make reports of all experimental data for the faculty researcher/supervisor.  Maintain the lab and equipment, update software, keep anti-virus software up to date. Make minor repairs when necessary. Distribute the universities Application Platform as a Service to the students at the university, and trouble shoot any service issues for users.

Designing GPU-accelerated digital-twin frameworks that fuse bulk and single-cell omics with mechanistic network models to predict and explain cellular behavior in real time. My work combines graph neural networks, agent-based simulation, and automated verification/uncertainty pipelines on UF’s HyperGator-AI supercomputer to advance precision-medicine research under Dr. Tamer Kahveci.

Masters degree in computer science incorporating : Machine learning Python programming for data science Data structures Computer architecture C/C++ programming Algorithm design and analysis web-database design data base design artificial intelligence