Skip to main content

Career objective

I strongly believe that Engineering is about building things and helping people - I’m highly motivated to contribute my skills towards this goal in my career.

  • Applying Data Science to Biology and Analytical HR domains
  • Consulting in Bioinformatics (infrastructure)
  • Organizing training workshops and capacity building

Academia

  • Master of Science (Data Science) - Liverpool John Moores University (March 2020 - January 2021)

  • Post-graduate diploma (Data Science) - IIIT Bangalore (April 2019 - March 2020)

  • Bachelor of Technology (Computer Science) - Delhi Technological University ( August 2012 - July 2016 )

Industry

  • Seqera Labs Engineer and Customer Solutions - (October 2020 - Present)
    • Working with the creators of Nextflow and Tower to enable teams to build better data pipelines - at scale.
    • Technologies: Nextflow, Groovy, Azure, AWS Batch, HPC orchestrators (SLURM/PBS)

  • BioSharp OÜ CEO and Lead Bioinformatician - (August 2020 - Present)
    • BioSharp works with clients on designing, building and deploying research projects in the bioinformatics space.
    • Technologies: Python, R, Nextflow, Groovy, Azure, F#, BioConda, Powershell, AWS Batch

  • Proximity Labs - Senior Software Engineer - (February 2020 - August 2020)
    • In my capacity as a consultant, I worked with premium international clients (such as Disney, ESPN and Hotstar) on the modernization of the popular cricket website espncricinfo.com with a multi-million user base.
    • Frontend: Implemented a performant progressive web app (PWA), with intuitive UX, performance and caching as the core concerns (TypeScript, ReactJS, NextJS).
    • Implemented the ad-injection system such as Bet365 etc along with the GDPR compliant analytics system.
    • Backend: Ported the monolithic Perl/MySQL based codebase into a modern micro-services architecture with a Core-API and Consumer-API based multi-tiered architecture to improve performance and caching.
    • Technologies: NextJS, TypeScript, MySQL, AWS, NestJS, Micro-services.

  • AlumnAI Academy - Head of Product - (March 2019 - June 2019)
    • AlumnAI aimed to help top universities build curriculum and recruit teachers for their AI and Data Science Master's degree programs.
    • Managed a team of 5 AI specialists to design and develop the AI and data-science curriculum material using TensorFlow, Scikit-learn.
    • Implemented an agile-based approach to curriculum development (sprints, weekly retrospection and demos etc)
    • Did user and competitor research to optimize the student experience.

  • Devnagri (Fourtek IT Solutions) - Machine Learning Engineer (August 2017 - December 2017)
    • Implemented custom parsers in Spacy fork for Indian languages like Hindi, Urdu and Punjabi etc.
    • Designed the implementation pipeline for automated translations before final corrections by human translators.
    • Was eventually promoted to CTO when the internal project I was building was spun off into its own company (see Devnagri above).
    • Technologies: Spacy, Keras, TensorFlow, AWS, Neo4J, Clojure, Python, Beautiful Soup

  • Peoplemetrix - Co-founder and Chief Technology Officer (August 2015 - July 2016)
    • Built a tool to drastically decrease the time taken for startup investing due-diligence process.
    • Fetch and visualize company data from various sources like LinkedIn, Owler, etc.
    • Built a visual comparison dashboard to make it easy to quickly gauge a startup in a comparative manner.
    • Technologies: D3.js, BackboneJS, Flask, MySql

Publications

(Please refer my ORCID for an updated list )

  • An Analytical Study to Find the Major Factors Behind the Great Smog of Delhi, 2016: Using Fundamental Data Sciences - Mentor Springer.
  • A Pilot Study for Phylogenetic Assessment of Mycobacterium bovis from Marajó Island, Brazil, based on Whole Genome Sequencing - Academia.edu.
  • Analysis of potential household transmission events of tuberculosis in the city of Belem, Brazil - Elsevier - Characterization of Mycobacterium tuberculosis var. africanum isolated from a patient with pulmonary tuberculosis in Brazil - Elsevier
  • Evaluation of drug susceptibility profile of Mycobacterium tuberculosis Lineage 1 from Brazil based on whole genome sequencing and phenotypic methods - Scielo
  • Molecular epidemiology of Mycobacterium tuberculosis in Brazil before the whole genome sequencing era: a literature review - Memorias.

Certifications

  • AWS Machine Learning Specialist Certification
  • Udacity A.I. Nanodegree

Miscellaneous

  • Technical reviewer for Packt Publications, books and accompanying author videos for titles like scikit-learn recipes and advanced-vim.
  • Mentored a cohort of 15 students for the Udacity AI NanoDegree with 13 students completing the term.
  • Weekend faculty for International School of Data Science and Artificial Intelligence