Stephen K.

Computational scientist with 5+ years delivering research-grade data science across clinical and biological domains. I build autonomous AI systems, scalable analysis pipelines, predictive models, and data-driven applications - with doctoral-level depth in multi-omics and systems biology. I adapt to your stack, your environment, and your standards. I do not just analyze data. I build infrastructure around it: reproducible workflows, intelligent agents, and production-ready solutions that hold up under scientific scrutiny. WHAT I OFFER Agentic AI and LLM Pipelines Autonomous agents, multi-agent systems, retrieval-augmented workflows, and LLM-integrated tools that automate complex reasoning and data tasks end to end. ML and Deep Learning Predictive modeling, neural networks, ensemble methods, and model interpretability - built to generalize, not overfit. Bioinformatics and Multi-Omics End-to-end analysis of next-generation sequencing data across modalities: bulk and single-cell RNA-seq, whole genome and exome sequencing, ATAC-seq, ChIP-seq, metagenomics, long-read sequencing, and spatial transcriptomics. Advanced integration techniques and multi-omics. Data Analysis and Visualization Statistical testing, exploratory analysis, and publication-quality figures that communicate results clearly to both technical and non-technical audiences. Biostatistics and Epidemiology Rigorous statistical modeling across biological and clinical datasets: survival analysis, mixed-effects models, longitudinal data analysis, Bayesian inference, multiple testing correction, and interpretation of population-scale and epidemiological data.​​​​​​​​​​​​​​​​ Scientific Pipelines and Software Containerized, HPC-compatible workflows built for reproducibility, portability, and scale - in whatever language or framework your project requires. Web and Application Development Interactive dashboards, REST APIs, and research tooling designed to make complex data accessible and actionable. Training, Tutoring and Consulting One-on-one and group tutoring in data science, bioinformatics, statistics, and programming, from foundational concepts to advanced techniques. I also consult with research teams looking to build internal capacity or accelerate ongoing projects. Whether you’re looking for support with a research project, building predictive models, or streamlining your data workflows, I’m here to help. Let’s bring your data to life.