My resumé


Hi, I’m Tim. I’m a full-stack engineer, but I have a doctorate in computational biology, and a lot of experience in applied machine learning. Therefore I’m also a “data scientist”. I’ve worked for some famous companies, like Twitch and Yelp, and founded two YCombinator-funded startups.

Professional Experience



Principal Scientist

I am working in a hybrid scientist/engineer role, developing and applying deep learning and other AI techniques to problems in rational drug design. It’s difficult and fun.



I co-created Omniref, a web application for annotating source code. Grew the site from nothing to hundreds of thousands of monthly unique visitors and tens of millions of pages. We graduated from the YCombinator winter 2015 batch, and raised significant seed funding from well-known investors.

In addition to all of the administrative and legal tasks, I wrote half of the code for the site (Ruby, Rails), wrote a number of popular blog posts (i.e. “marketing”) and did all other user outreach.



Vayable was a marketplace for unique tours and travel experiences. Graduated from the YCombinator summer 2012 batch, and raised outside funding from top angel and venture investors. We were covered extensively by the New York Times, Fortune, and many others.

In addition to writing all of the code for the original site (Ruby, Rails), I interviewed, hired, managed a team of engineers, coordinated product development, and did basically anything else that needed to be done.


Senior Engineer

I was early member of Yelp’s search and data-mining team, and a “data scientist” before the term existed. I wrote Yelp’s A/B testing framework (Python), and developed infrastructure for the real-time gathering and analysis of site metrics (Hadoop, HDFS, MySQL, enormous gobs of Python).

Years before the advent of frameworks like Apache Spark, my system was processing hundreds of gigabytes of data daily, and touched every pageview on (at that time, over a hundred million monthly unique visitors). I don’t know if this counts as “big data” today, but it definitely wasn’t small data at the time. (was


Senior Engineer

I was one of the first engineers for the site that became responsible for the design, development and maintenance of major features that still exist today. Some of my accomplishments:

  • Developed a pro account feature and oversaw its development into a source of millions of dollars in annual revenue.

  • Built and maintained a software infrastructure for payments that handled tens of thousands of transactions every month (before Stripe, Braintree, etc. existed)

  • Created a real-time storage infrastructure used to archive over hundreds of TB of video in our datacenter, ultimately saving millions in bandwith and storage costs.


PhD, Computational Biology (Biochemistry)

University of Washington

Dissertation: “Development of statistical potential functions for the prediction of protein-nucleic acid interactions from structure.”

My dissertation research was in computational structural biology, on the application of machine learning algorithms to the problem of predicting protein-DNA interactions from structure. (You’ve watched NOVA and seen scientists spinning molecules around on computer screens? Yeah, that’s actually what I did. Plus some math.)

BS, Computer Science and Biology

University of Denver

I was a double major in CS and Biology. I studied a lot.

Technology buzzword bingo

Like most experienced programmers, I can (and do) pick up new things quickly. I’ve worked with a huge number of platforms, libraries and tools, but if it helps, here’s a non-exhaustive list of common technologies that I have used professionally:

Ruby, Rails, Python, ECMAScript/Javascript, Java, C++, C, R, Memcached, HAProxy, Boost, Twisted, ElasticSearch, Lucene, Hadoop, HDFS, Postgres, MySQL, Nginx, Apache, Linux, Git, HTML, CSS, SCSS, Slim, HAML, Heroku, AWS, S3, EC2, RDS, CloudFront, Route53

Here’s some of the “data science” skills I have used professionally:

Supervised/unsupervised learning, Bayesian classifiers, Linear regression, Logistic regression, SVM, Random forests, Clustering (kNN, k-means, hierarchical, etc.), ANOVA, Principal Component Analysis, Descriptive statistics, Probability theory


  • Robertson, T., Varani, G. (2009) “Prediction of protein-nucleic acid interactions.” In: Structural Bioinformatics, 2nd ed. Bourne, P. and Gu, J., eds. Wiley-Liss, Hoboken, NJ.

  • Zheng, S., Robertson, T., Varani, G. (2007). A knowledge-based potential function predicts the specificity and binding energy of RNA-binding proteins. FEBS J., 274, 6378-6391

  • Robertson, T., Varani, G. (2007). An all-atom, distance-dependent scoring function for the prediction of protein-DNA interactions from structure. Proteins, 66, 359-374.

  • Chen, Y., Kortemme, T., Robertson, T., Baker, D., Varani, G. (2004).
    A new hydrogen-bonding potential for the design of protein-RNA interactions predicts specific contacts and discriminates decoys.
    Nucleic Acids Res, 32, 5147-62.

  • Chivian, D., Kim, D.E., Malmstrom, L., Bradley, P., Robertson, T., Murphy, P., Strauss, C.E.M., Bonneau, R., Rohl, C.A., Baker, D. (2003). Automated prediction of CASP-5 structures using the Robetta server. Proteins, 53 (suppl. 6), 524-33.

  • Chivian, D., Robertson, T., Baker, D. (2003). “Ab initio methods” (pp. 547-557). In: Structural Bioinformatics, Bourne, P. and Weissig, H., eds. Wiley-Liss, Hoboken, NJ.

  • Bonneau, R., Strauss, C.E.M., Rohl, C.A., Chivian, D., Bradley, P., Malmstrom, L., Robertson, T., Baker, D. (2002). De novo prediction of three-dimensional structures for major protein families.
    J Mol Biol, 322, 65-78.
© 2017, Tim Robertson