resume.json

{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Edmund Miller","label":"Bioinformatics Engineer | AI in Life Sciences | PhD Molecular Biology","image":"https://0.gravatar.com/avatar/765e027729c5964a4e5c83b90d6013bb9029b41ef2be474c2fee3eac3ba2be28","email":"hello@edmundmiller.dev","phone":"214-532-3452","url":"https://edmundmiller.dev","summary":"","location":{"countryCode":"US","address":"United States"},"profiles":[{"url":"https://github.com/edmundmiller","username":"edmundmiller","network":"github"},{"network":"LinkedIn","username":"edmundmiller","url":"https://www.linkedin.com/in/edmundmiller/"},{"network":"Mastodon","username":"@emiller@genomic.social","url":"https://genomic.social/@emiller"},{"network":"ORCiD","username":"0000-0002-2398-0334","url":"https://orcid.org/0000-0002-2398-0334"},{"network":"Twitter","username":"E_miller88","url":"https://twitter.com/E_miller88"}]},"work":[{"name":"Seqera","position":"Bioinformatics Engineer","startDate":"2024-12-01","endDate":"","highlights":["Split between customer-facing scientific engagement and the AI Engineering team, leading end-to-end AI product rollout for life sciences customers across pharma, biotech, and research institutions.","Design AI validation framework and evaluation benchmarks, defining acceptance criteria for model outputs in regulated scientific contexts.","Establish technical integrations with Nvidia GPU infrastructure and Databricks, enabling accelerated computing and unified data platforms for customer genomics workflows.","Co-led ground-up rewrite of Seqera AI agent (v2) with the AI Engineering team, improving architecture, capabilities, and reliability of the flagship AI product."],"summary":null,"url":"https://seqera.io","location":"Remote"},{"name":"The University of Texas at Dallas","position":"Instructor - Applied Genomics","startDate":"2020-06-01","endDate":"2024-08-01","highlights":["Designed from scratch a graduate-level computational biology course teaching biology students practical bioinformatics skills, covering NGS data analysis, workflow development, version control, HPC computing, and reproducible research practices.","Pioneered pedagogical transformation by adopting AI-assisted coding tools (GitHub Copilot, 2022-2024), fundamentally shifting the teaching approach from syntax-focused instruction to conceptual understanding—students could focus on biological questions and computational thinking while AI tools handled code scaffolding.","Experienced firsthand the transformative impact of AI on education: pre-AI courses (2020-2021) struggled with syntax barriers limiting content coverage; post-AI courses (2022-2024) achieved significantly deeper engagement with genomics concepts and analysis workflows.","Course became required for the Genomics Graduate Certificate program, establishing it as a foundational component of the university's computational biology curriculum and reaching 30+ graduate students across five summer sessions."],"summary":null,"url":"https://catalog.utdallas.edu/","location":"Richardson, TX"},{"name":"nf-core","position":"Core Team Member","startDate":"2020-03-01","endDate":"","highlights":["Drive community-wide adoption of nf-test evaluation framework, establishing validation standards used across 100+ production bioinformatics pipelines.","Conduct technical reviews of community-contributed pipelines and modules, enforcing reproducibility standards and best practices compliance.","Architect nf-core/nascent pipeline and distill development practices into reusable templates, CI/CD workflows, and documentation standards adopted ecosystem-wide.","Deliver technical presentations on evaluation frameworks and pipeline validation at nf-core/bytesize webinars and Nextflow Summit conferences."],"summary":null,"url":"https://nf-co.re","location":"Remote"},{"name":"Element Biosciences","position":"Bioinformatics Engineering Associate","startDate":"2021-08-10","endDate":"2023-02-28","highlights":["Architected automated secondary analysis system and built internal genomic assay analysis infrastructure, reducing manual intervention and standardizing quality control across all sequencing platforms.","Presented secondary analysis automation architecture at Nextflow Summit 2022, demonstrating significant reduction in analysis turnaround time.","Re-engineered inherited legacy workflow from Python/Azure to Nextflow, achieving 92% cost reduction (from $500+ to $40 per sample) while improving scalability and reproducibility.","Redesigned tertiary analysis infrastructure and performed variant interpretation, tumor mutational burden assessment, and clinical reporting for oncology applications.","Developed TumorNormal somatic variant calling pipeline for cancer genomics, integrating best-practice tools for detecting mutations in matched tumor-normal samples."],"summary":null,"url":"https://www.elementbiosciences.com","location":"Remote"},{"name":"Element Biosciences","position":"Bioinformatics Engineering Intern","startDate":"2021-06-01","endDate":"2021-08-10","highlights":["Modernized internal whole genome sequencing pipeline by migrating from Jupyter notebooks and bash scripts to Nextflow, enabling reproducibility, scalability, and version control.","Executed SARS-CoV-2 variant calling analysis on COVID-19 AmpliSeq samples, identifying viral mutations and tracking strain prevalence.","Analyzed 10x Visium spatial transcriptomics datasets, performing tissue architecture mapping, cell type deconvolution, and spatially-resolved gene expression profiling.","Established company-wide Nextflow module standards, MultiQC integration guidelines, and automated testing frameworks, adopted across all bioinformatics pipelines.","Validated sequencing quality and quantified RNA-seq accuracy using ERCC spike-in controls, establishing baseline performance metrics for platform validation."],"summary":null,"url":"https://www.elementbiosciences.com","location":"Remote"},{"name":"Olypsis Technologies","position":"Blockchain Software Engineer","startDate":"2018-06-30","endDate":"2020-06-30","earlyCareer":true,"cvOnly":true,"highlights":["Led development and design of BlockNKey system, implementing comprehensive test suite for legacy code, containerizing infrastructure, and architecting REST API with smart contracts for decentralized authentication.","Developed ERC20-compliant payment distribution smart contract in Solidity for Digital Assets Foundry, automating revenue sharing among multiple stakeholders.","Architected DAWN protocol for peer-to-peer file transfer using distributed hash tables and cryptographic verification, eliminating reliance on trusted third parties.","Integrated Web3 stack including Whisper messaging, IPFS distributed storage, and AES-256 encryption into decentralized applications built with React."],"summary":null,"url":"https://www.linkedin.com/company/30006902","location":"Remote"},{"name":"Functional Genomics Lab (Prof. Tae Hoon Kim)","position":"Student Researcher","startDate":"2015-07-01","endDate":"2020-08-01","cvOnly":true,"highlights":["Developed Snakemake pipeline for enhancer RNA (eRNA) prediction, reproducing published results and identifying novel eRNA candidates through integrated analysis of nascent transcription data.","Implemented reproducible computational workflows using containerization, Conda environment management, and HPC cluster scheduling to enable collaborative research.","Deployed JupyterHub collaborative environment and established documentation infrastructure, improving lab-wide computational reproducibility and knowledge sharing.","Designed PCR primers for cell identification, target transcripts, and genotyping.","Genotyped and organized the lab's knockout mouse colonies.","Dissected mice to retrieve the frontal cortex and cultured neuronal cells.","Performed RNA isolation from cells treated with LPS particles and used qPCR to quantify eRNA transcript levels."],"summary":null,"url":"https://labs.utdallas.edu/kim-lab/","location":"Richardson, TX"},{"name":"Millblock LLC","position":"Co-founder","startDate":"2017-09-01","endDate":"2020-06-01","earlyCareer":true,"cvOnly":true,"highlights":["Conducted technical due diligence on blockchain infrastructure projects, evaluating smart contract security, tokenomics, and development team capabilities for investment decisions.","Recruited and managed technical contractors for blockchain development, smart contract auditing, and web3 application deployment projects."],"summary":null,"url":"","location":"Richardson, TX"},{"name":"Paul G. Hull, MD","position":"Apprentice","startDate":"2014-05-01","endDate":"2016-08-01","earlyCareer":true,"cvOnly":true,"highlights":["Learned general diagnostic techniques","Sutured patients' wounds after procedures.","Administered various injections to the patients.","Drew blood for routine blood tests.","Learned to interpret EKGs"],"summary":null,"url":"","location":"Plano, TX"}],"volunteer":[{"organization":"Dallas Blockchain","position":"Core Member","startDate":"2017-06-01","endDate":"2020-06-01","summary":"","highlights":[],"url":"","earlyCareer":true,"cvOnly":true},{"organization":"Artificial Intelligence Society","position":"Member","startDate":"2016-09-01","endDate":"2019-05-01","summary":"","highlights":[],"url":"","earlyCareer":true,"cvOnly":true},{"organization":"Academic Excellence Scholarship","position":"Freshman Mentor","startDate":"2016-08-01","endDate":"2016-12-01","summary":"","highlights":[],"url":"","earlyCareer":true,"cvOnly":true},{"organization":"UT Dallas Rugby Football Club","position":"Captain","startDate":"2015-08-01","endDate":"2019-05-01","summary":"","highlights":["2015-2016 Rookie of the Year","2016-2018 President","2017-2018 Most Valuable Back","Created & Maintained Club Website"],"url":"","earlyCareer":true,"cvOnly":true}],"education":[{"institution":"The University of Texas at Dallas","area":"Molecular and Cell Biology","studyType":"Doctor of Philosophy - PhD","startDate":"2020-08-20","endDate":"2025-05-12","score":"","courses":[],"dissertation":"Standardized Computational Infrastructure for Nascent Transcript Analysis: Addressing Reproducibility Challenges in Enhancer RNA Discovery","highlights":[]},{"institution":"The University of Texas at Dallas","area":"Molecular and Cell Biology","studyType":"Master of Science - MS","startDate":"2020-08-20","endDate":"2025-05-12","score":"","courses":[]},{"institution":"The University of Texas at Dallas","area":"Biotechnology","studyType":"Master of Science - MS","startDate":"2018-08-20","endDate":"2019-12-13","score":"","courses":[],"highlights":["Academic Excellence Scholarship 2015-2019","Fast-Track Program"]},{"institution":"The University of Texas at Dallas","area":"Molecular Biology","studyType":"Bachelor of Science - BS","startDate":"2015-08-20","endDate":"2018-08-04","score":"","courses":[],"highlights":["Academic Excellence Scholarship 2015-2019","President's Scholarship 2016-2017","Continuing Student Scholarship 2017-2018"]}],"awards":[{"title":"Third Place Status Bounty","date":"2019-02-01","awarder":"ETHDenver","summary":"Proof of Opossum: A decentralized voting app for the best Status nickname that made use of Formatic, GraphQL, the Graph, Openzeppelin-SDK, and Status extensions.","url":"https://github.com/Emiller88/proof-of-opossum","earlyCareer":true,"cvOnly":true},{"title":"First Place Set & Second Place ChainLink","date":"2018-10-01","awarder":"ETHSF","summary":"Link Set","url":"https://github.com/Emiller88/Link-Set","earlyCareer":true,"cvOnly":true},{"title":"Second Place","date":"2018-01-01","awarder":"CometHacks","summary":"RotoHive: Created smart contracts for a fantasy sports dapp based on Numerai.","url":"https://github.com/Emiller88/Rotohive","earlyCareer":true,"cvOnly":true}],"certificates":[],"publications":[{"name":"Empowering bioinformatics communities with Nextflow and nf-core","publisher":"Genome Biology","releaseDate":"2025-07-29","url":"https://doi.org/10.1186/s13059-025-03673-9","summary":"The nf-core community develops and maintains a diverse suite of over 100 high-quality bioinformatics pipelines built using Nextflow.","authorPosition":"Co-author"},{"name":"Scalable and efficient DNA sequencing analysis on different compute infrastructures aiding variant discovery","publisher":"NAR Genomics and Bioinformatics","releaseDate":"2024-03-01","url":"https://doi.org/10.1093/nargab/lqae031","summary":"DNA variation analysis has become indispensable in many aspects of modern biomedicine, most prominently in the comparison of normal and tumor samples. Thousands of samples are collected in local sequencing efforts and public databases requiring highly scalable, portable, and automated workflows for streamlined processing. Here, we present nf-core/sarek 3, a well-established, comprehensive variant calling and annotation pipeline for germline and somatic samples. It is suitable for any genome with a known reference. We present a full rewrite of the original pipeline showing a significant reduction of storage requirements by using the CRAM format and runtime by increasing intra-sample parallelization. Both are leading to a 70% cost reduction in commercial clouds enabling users to do large-scale and cross-platform data analysis while keeping costs and CO2 emissions low. The code is available at https://nf-co.re/sarek.","authorPosition":"Co-author"},{"name":"Sequencing by avidity enables high accuracy with low reagent consumption","publisher":"Nature Biotechnology","releaseDate":"2023-05-25","url":"https://doi.org/10.1038/s41587-023-01750-7","summary":"We present avidity sequencing, a sequencing chemistry that separately optimizes the processes of stepping along a DNA template and that of identifying each nucleotide within the template. Nucleotide identification uses multivalent nucleotide ligands on dye-labeled cores to form polymerase–polymer–nucleotide complexes bound to clonal copies of DNA targets. These polymer–nucleotide substrates, termed avidites, decrease the required concentration of reporting nucleotides from micromolar to nanomolar and yield negligible dissociation rates. Avidity sequencing achieves high accuracy, with 96.2% and 85.4% of base calls having an average of one error per 1,000 and 10,000 base pairs, respectively. We show that the average error rate of avidity sequencing remained stable following a long homopolymer.","authorPosition":"Co-author"},{"name":"mlf-core: a framework for deterministic machine learning","publisher":"Bioinformatics","releaseDate":"2023-04-03","url":"https://doi.org/10.1093/bioinformatics/btad164","summary":"Machine learning has shown extensive growth in recent years and is now routinely applied to sensitive areas. To allow appropriate verification of predictive models before deployment, models must be deterministic. Solely fixing all random seeds is not sufficient for deterministic machine learning, as major machine learning libraries default to the usage of nondeterministic algorithms based on atomic operations.","authorPosition":"Co-author"}],"skills":[{"name":"Bioinformatics","level":"5","keywords":["Nextflow","Seqera Platform","Snakemake","Genomics","NGS"]},{"name":"AI/ML Deployment","level":"5","keywords":["GenAI Deployment","LLM Evaluation","AI Validation","RAG Pipelines","Model Integration"]},{"name":"Computational Biology","level":"5","keywords":["Rust","Python"]},{"name":"High Performance Computing","level":"5","keywords":["Linux","Slurm","Kubernetes","AWS Batch"]},{"name":"DevOPs","level":"5","keywords":["Linux","NixOS","Kubernetes","GitHub Actions","AWS","Terraform","Ansible"]},{"name":"Software Packaging","level":"","keywords":["nix","Docker","Singularity","Conda"]},{"name":"Data Science","level":"","keywords":["Python","Julia","SQL","DuckDB","Machine Learning","Deep Learning","LLMs"]},{"name":"Decentralized Computing","level":"4","keywords":["IPFS","Ethereum","Solidity","web3.js","Whisper"]},{"name":"Web Development","level":"3","keywords":["Typescript","Vue","Astro","Deno","React","HTML","CSS","JavaScript"]}],"interests":[],"references":[],"projects":[{"name":"nf-core/nascent","startDate":"2020-03-20","description":"Nascent Transcription Processing Pipeline","url":"https://github.com/nf-core/nascent","role":"Lead Maintainer"},{"name":"nextflow-mode","startDate":"2021-01-01","description":"An Emacs mode for syntax highlighting for Nextflow based on snakemake-mode","url":"https://github.com/edmundmiller/nextflow-mode","role":"Creator"},{"name":"Doom-Emacs","startDate":"2018-03-01","description":"Worked on Reference, Conda, and Solidity modules. Integrated GitHub action for CI Testing. Helped new users become familiar with Doom's conventions.","url":"https://github.com/hlissner/doom-emacs","role":"Contributor","cvOnly":true,"earlyCareer":true},{"name":"edgePy","startDate":"2018-09-01","endDate":"2018-12-01","description":"A Python implementation of edgeR for differential expression analysis. Implementing code and testing standards to the repo.","url":"https://github.com/r-bioinformatics/edgePy","role":"Contributor","cvOnly":true,"earlyCareer":true}],"meta":{"version":"v1.0.0","canonical":"https://github.com/jsonresume/resume-schema/blob/v1.0.0/schema.json"}}

hey @edmundmiller each of your work sections needs a summary

Thanks! I was just tossing this up here to try to consume it in a nix-flake.