resume.json

resume.json

{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/refs/heads/master/schema.json",
  "basics": {
    "name": "Marius van Niekerk",
    "label": "Data platform architect",
    "image": "https://gravatar.com/avatar/55e8617922535a57ee1db254de5aa34c?size=512",
    "email": "[email protected]",
    "phone": "919-985-9072",
    "summary": "As both a software developer and a statistician I have a keen insight into how data scientists want to write code, and how to deploy that to production environments.  On the spectrum of data science, I lean much more heavily towards the software engineering side.\n\nI believe in getting working solutions off the ground as quickly as possible with rapid iteration cycles.  I enjoy picking up new tools, languages, and codebases as projects require them.\n\nI'm an active proponent and contributor to various open source initiatives.",
    "location": {
      "countryCode": "US",
      "address": "United States",
      "city": "Raleigh",
      "region": "North Carolina"
    },
    "profiles": [
      {
        "network": "LinkedIn",
        "username": "mariusvniekerk",
        "url": "https://www.linkedin.com/in/mariusvniekerk/"
      },
      {
        "network": "Twitter",
        "username": "__mvn__",
        "url": "https://twitter.com/__mvn__"
      },
      {
        "network": "GitHub",
        "username": "mariusvniekerk",
        "url": "https://github.com/mariusvniekerk"
      }
    ]
  },
  "volunteer": [
    {
      "organization": "conda-forge",
      "position": "core contributor",
      "startDate": "2018-03-31",
      "highlights": [
        "Developed several of the parts of conda-smithy, a tool to dynamically generate build recipe repositories for conda packaging",
        "Conda-lock a lightweight locking mechanism to aid in reproducibility of conda environments."
      ],
      "summary": "Core maintainer for conda-forge",
      "website": "https://conda-forge.org/"
    },
    {
      "organization": "conda",
      "position": "Steering council member",
      "startDate": "2022-06-18",
      "highlights": [
      ],
      "summary": "Help to drive standards and best practices for the conda ecosystem",
      "website": "https://conda.io/"
    }
  ],
  "work": [
    {
      "name": "Voltron Data",
      "location": "remote", 
      "description": "A next-generation data system startup focused on GPU-accelerated data processing",
      "company": "Voltron Data",
      "position": "Senior Staff Software Engineer",
      "startDate": "2021-08-30",
      "highlights": [
        "Architected and owned the set of client-facing gRPC services that surround the GPU-accelerated Theseus compute engine",
        "Developed a custom Kubernetes Operator that manages the lifecycle of GPU accelerated compute jobs",
        "Build out benchmarking and performance testing infrastructure for the Theseus compute engine"
      ],
      "website": "https://www.voltrondata.com",
      "summary": "Tech Lead building and architecting tools and services to support the Theseus compute engine."
    },
    {
      "name": "Flatiron Health",
      "description": "An Oncology Health-Tech company",
      "location": "New York, NY",
      "company": "Flatiron Health",
      "position": "Staff Software Engineer",
      "startDate": "2017-03-31",
      "endDate": "2021-08-30",
      "highlights": [
        "Architect for the core platform organization (40+ engineers)",
        "Migrated a large legacy ETL framework written in bash to a modern python equivalent using dask whilst maintaining full backwards compatibility",
        "Deployed Snowflake at enterprise scale",
        "Developed a simple S3-based data catalog system for archival datasets with atomicity guarantees and versioning",
        "Migrated petabytes of datasets from csv to parquet"
      ],
      "summary": "Build, design and maintain tools and architecture to aid in the processing of electronic health record based datasets.",
      "website": "https://www.flatiron.com"
    },
    {
      "name": "Maxpoint Interactive",
      "description": "Ad-tech focusing on geospatial targeting",
      "company": "MaxPoint Interactive",
      "position": "Senior Computational Engineer",
      "startDate": "2016-04-30",
      "endDate": "2017-02-28",
      "location": "Raleigh, NC",
      "highlights": [
        "A cross-language framework for building data pipelines using Apache Spark. This allows data scientists to to write code in python and easily move it to a production process written in Scala.",
        "Large scale geo-spatial analysis model that performs matching between billions of GPS points and millions of addresses with Apache Spark to effectively compute approximations of home locations from observations of noisy GPS data."
      ],
      "summary": "Worked as a tool builder and facilitator between the data science team and the data engineering team. \n\nParticular focus was on scaling solutions to work on massive datasets (10 billion+ rows).\n\nLots of big data work using hive, impala, spark, and MapReduce.",
      "website": "https://www.linkedin.com/company/503560"
    },
    {
      "name": "Maxpoint Interactive",
      "description": "Ad-tech focusing on geospatial targeting",
      "company": "MaxPoint Interactive",
      "position": "Senior Data Scientist ",
      "startDate": "2012-04-30",
      "endDate": "2016-04-30",
      "location": "Raleigh, NC",
      "highlights": [
        "A dynamic ad serving product based on real-time weather conditions.",
        "An in-house monitoring and alerting web application used by all account managers and analysts to manage active advertising campaigns (~$150M in spend).",
        "A Prediction algorithm for detecting non-human web traffic using boosted trees."
      ],
      "summary": "Primary support for a team of 23 data scientists, 17 engineers and 21 analysts for moving scientific applications to production.  Team lead for a team of computational engineers.  Built various smaller ad-hoc solutions for business problems on very short time scales.  Drove key technology decisions working with the CTO directly around which big data technologies to focus our efforts on. ",
      "website": "https://www.linkedin.com/company/503560"
    },
    {
      "company": "CIMSO",
      "name": "CIMSO",
      "position": "Software Engineer",
      "startDate": "2007-06-30",
      "endDate": "2012-03-31",
      "location": "Stellenbosch, South Africa",
      "highlights": [
        "Implemented an online hotel reservation portal in web2py with live synchronization to the rest of the software suite.",
        "Embedded LibreOffice inside the hotel management application with the purpose of allowing for unified storage and management of documents.", 
        "Developed a generic database abstraction layer. The database abstraction layer provides statically typed wrappers around any given database table with flexible code generation in order to support multiple database architectures.",
        "Developed a generic reporting engine that supports arbitrary grouping of data with the purpose of providing customizable reports for hotel and financial management."
      ],
      "summary": "Design, enhancement, optimization and maintenance of a large Delphi-based hospitality focused desktop software suite deployed throughout Africa and South East Asia.",
      "website": "https://www.cimso.com/"
    }
  ],
  "education": [
    {
      "institution": "Stellenbosch University",
      "area": "Mathematical Statistics",
      "studyType": "Master of Science",
      "startDate": "2008-12-31",
      "endDate": "2012-12-31",
      "gpa": "",
      "courses": []
    },
    {
      "institution": "University of Stellenbosch",
      "area": "Mathematical Statistics",
      "studyType": "Bachelor of Science (Honours)",
      "startDate": "2007-12-31",
      "endDate": "2007-12-31",
      "gpa": "",
      "courses": []
    },
    {
      "institution": "University of Stellenbosch",
      "area": "Actuarial Science",
      "studyType": "Bachelor of Commerce",
      "startDate": "2004-12-31",
      "endDate": "2006-12-31",
      "gpa": "",
      "courses": []
    }
  ],
  "awards": [],
  "publications": [],
  "skills": [
    {
      "name": "Programming languages",
      "level": "",
      "keywords": ["Python", "Go", "Rust", "Scala", "Delphi", "R"]
    },
    {
      "name": "Notable software libraries with extensive experience",
      "level": "",
      "keywords": ["Conda", "gRPC", "Earthly", "Dask", "Apache Arrow", "Apache Spark", "Jupyter stack", "Apache Airflow"]
    },
    {
      "name": "Devops Tools",
      "level": "",
      "keywords": ["Kubernetes", "Terraform", "Pulumi", "Github Actions", "Ansible", "Chef"]
    },
    {
      "name": "Cloud Experience",
      "level": "",
      "keywords": ["AWS", "GCP"]
    }
  ],
  "languages": [
    {
      "language": "English",
      "fluency": "Native Speaker"
    },
    {
      "language": "Afrikaans",
      "fluency": "Native Speaker"
    }
  ],
  "interests": [
    {
      "name": "Wine"
    },
    {
      "name": "Cooking"
    }
  ],
  "references": [
  ],
  "projects": [],
  "meta": {
    "version": "v1.2.1",
    "canonical": "https://github.com/jsonresume/resume-schema/blob/v1.2.1/schema.json",
    "theme": "kendall"
  }
}