John Markos O'Neill

Data mining, machine learning, anti-spam, bioinformatics

San Francisco Bay Area

Current
  • Senior Software Engineer at Zvents
Past
Education
  • St. John's College
  • St. John's College
Connections
296 connections
Industry
Computer Software
Websites

John Markos O'Neill’s Summary

Over ten years of experience in data mining and analysis, informatics, and software development, working for public, private, and non-profit firms. Technical application lead of a multi-million dollar project. Experience in machine learning, anti-spam, and distributed computing, working directly with customers and users to make their jobs easier.

John Markos O'Neill’s Specialties:

Machine learning, data mining, data analysis, anti-spam, e-mail, dataflow, bioinformatics, Linux, Ruby on Rails, Perl, distributed computing, startups, workflow design


John Markos O'Neill’s Experience

  • Senior Software Engineer

    Zvents

    (Privately Held; 11-50 employees; Internet industry)

    September 2008Present (11 months)

    I'm building data mining and content analysis tools to help create the world's most advanced and usable local search.

  • Research Engineer

    Zvents

    (Privately Held; 11-50 employees; Internet industry)

    November 2006September 2008 (1 year 11 months)

    Developed and automated tools for content insertion, analysis, and publication.

  • Senior Data Engineer

    Proofpoint

    (Privately Held; Computer Software industry)

    January 2005November 2006 (1 year 11 months)

    Designed and implemented new classifier features and improvements to data architecture.
    Machine learning combined with rapid response to emerging spam campaigns increased classifier effectiveness and accuracy.

  • Data Engineer

    Proofpoint

    (Privately Held; Computer Software industry)

    January 2004January 2005 (1 year 1 month)

    Data mining and updates of Proofpoint's anti-spam classifier models.
    Generated new features based on emerging spam attacks.
    Analyzed and captured spam messages for update process.
    Worked with customers to stop emerging spam campaigns.

  • Systems Programmer/Unix Account Manager

    Incyte Genomics

    (Public Company; INCY; Biotechnology industry)

    July 2001November 2002 (1 year 5 months)

    Managed Unix and Linux accounts for over 100 users in a production bioinformatics, dataflow, and data analysis environment.
    Administered production Unix and Linux machines.
    Configured Platform LSF distributed computing cluster of over 1,000 machines. Automated cluster status reporting.

  • Bioinformatics Programmer

    Incyte Genomics

    (Public Company; INCY; Biotechnology industry)

    June 1999July 2001 (2 years 2 months)

    Technical application lead on Linux farm project, which was both used in-house and sold to outside customers. Co-designed, wrote, documented, and maintained job distribution software, as well as a parallel application launcher, for several clusters of Pentium computers, controlling over 2,000 CPUs in total.
    The project saved Incyte several million dollars in hardware costs by moving the majority of data processing from expensive servers to much cheaper PCs.

  • Senior Bioinformatics Associate

    Incyte Pharmaceuticals

    (Public Company; INCY; Biotechnology industry)

    November 1997June 1999 (1 year 8 months)

    Ran dataflow for Incyte's plant database, defining schedules between sequencing, product science, and legal departments. Screened and annotated several hundred thousand sequences, analyzing and preparing them for release, meeting an aggressive schedule.
    Wrote wrapper scripts to automate dataflow.
    Benchmarked different hardware platforms to evaluate cost/performance. This work led to the Linux farm project.

  • Bioinformatics Associate

    National Center for Genome Resources

    (Non-Profit; Biotechnology industry)

    June 1994August 1997 (3 years 3 months)

    Annotated and curated Genome Sequence DataBase (GSDB), a public DNA sequence database. GSDB was a major project of the non-profit National Center for Genome Resources (NCGR).
    Served as primary contact for four large genome centers, processing large and multiple sequence submissions into the relational database.
    Tested and evaluated GSDB Annotator software.

  • GenBank Annotator

    Los Alamos National Laboratory

    (Government Agency; Research industry)

    August 1993June 1994 (11 months)

    Trained offsite users in DNA sequence file format, answering detailed questions about data insertion.
    Assured data quality by checking submissions for correct syntax and accurate biological information.


John Markos O'Neill’s Education

  • St. John's College

    B.A. , Liberal Arts , 19911993

  • St. John's College

    Liberal Arts 19891991


Additional Information

John Markos O'Neill’s Websites:

John Markos O'Neill’s Interests:

programming, scripting, Ruby on Rails, Ruby, Perl, Linux, distributed computing, events, search, startups, bioinformatics, genome, genomics, machine learning, anti-spam, GTD, environment, sustainability, ecological footprint, renewable energy, bicycling, ethics, free speech, free culture


John Markos O'Neill’s Contact Settings

Interested In:

  • career opportunities
  • new ventures
  • job inquiries
  • expertise requests
  • reference requests
  • getting back in touch

Public profile powered by: LinkedIn

Create a public profile: Sign In or Join Now

View John Markos O'Neill’s full profile:

  • See who you and John Markos O'Neill know in common
  • Get introduced to John Markos O'Neill
  • Contact John Markos O'Neill directly

View Full Profile