Christopher Walker Email & Phone Number

San Francisco, California, Us

* Data wrangling and web engineering in support of marvelous.ai core NLP components* Co-chair, MisinfoSec Working Group, Credibility Coalition

San Francisco, California, Us

Responsible for all backend and data analytics stacks at seed-stage startup:* End-to-end scraper, DB and search index management* Machine Learning and text analytics components including classification, clustering, search, named-entity recognition and entity resolution.* Major technologies used: Postgres, python, flask, SQL-alchemy, graphlab (SVM, logistic regression, lda and k-means), elasticsearch, scipy, numpy, nltk, Stanford classifier

San Francisco, California, Us

Completely rebuilt a seed-stage Rails prototype as a modern SaaS offering:* Pulled disparate crawling and scraping components together into unified content store* Pulled loosely coupled extraction and clustering technologies together into a formal Spark-based build pipeline* Reframed out of the box SOLR components with Scala-based ranking and classification* Rewrote the Rails server components as JSON API using jRuby Sinatra* Rewrote the Rails application components as a single page Ember JS applicationTransitioned 10-15 member engineering team from “seed” to “Series A” processes* Established teams, leads and functional groups* Introduced team-based Agile and sprint-based planning* Established sprint-based backend builds and metrics-driven development* Established continuous integration for product release* Coached 5+ junior staff on team leadership and project management* Introduced code review and style guidelines* Established documentation best practices* Established multi-sprint planning processesManaged the successful development of several ML and NLP features, including:* Per-citation case law sentiment analysis* Judge co-citation analytics* Indirect citation extraction and resolution* Duplicate citation resolution* Outcome detection and classificationSignificant hands-on full-stack development responsibilities at a small enterprise software startup Technologies used: AWS, Chef, Spark, SOLR, Scala, ruby/jruby, Sinatra, Rails, MongoDB, MySQL, Ember JS, jquery, D3/Canvas/SVG, Java, Stanford Classifier

Christopher is responsible for all of the data idibon works with from scraping and cleaning to machine learning and classification. He is also tasked with applying his world-class experience to the problem of efficiently injecting "the human in the loop" using state of the art active learning to optimize crowd-sourcing efforts.* Significant hands-on full-stack development responsibilities at a small seed-stage enterprise software startup. Major technologies include: Rails, Sinatra, Storm, Hadoop, Riak, MySQL, Redis, Capistrano, AWS, git/github, Ruby, JRuby, rspec, Java, Bootstrap, Javascript, JQuery, D3.js, Twitter Firehose (Datasift & gnip) and the Stanford Classifier.* Responsible for all data management at idibon: from scraping and cleaning to machine learning and classification.* Responsible for HCI (Human-Computer Interaction) interfaces for manipulating and aggregating language data

Philadelphia, Pennsylvania, Us

Diverse management, technical and linguistic responsibilities* 15 direct full-time reports (including 3 PhDs)Extensive “turn-around specialist” responsibilities for a 20 year old academic software program:* Established team-based development with a progressively more Agile model* Established version-control practices (with Git and Github)* Established ticketing and tracking practices (with Atlassian JIRA)* Began transition to TDD (and BDD and, ultimately, CI)* Related trivia too numerous to listToolkit, infrastructure and corpus development for numerous HLT projects, including:* NIST: OpenMT12 Evaluation* NIST: Text Analysis Conference: Knowledge Base Population (TACKBP)* NIST: Multilingual Automatic Document Classification Analysis and Translation (MADCAT)* Machine Reading* Speaker Identification* Speech Event Detection* Video Event DetectionWeb and text/data-processing development in numerous languages and frameworks, including: Ruby (including: RSpec, dRuby and Rails), Python, SQL, MongoDB, Git, Selenium, Javascript (especially JQuery/AJAX and JSON), R and others.

Us

Diverse management, technical and linguistic responsibilities, including:* 4 direct full-time reports (2 PhDs)* 20+ indirect part-time reportsNatural Language Processing (NLP) Programming in multiple languages: Ruby, Perl, C#Multiple Human Language Technology (HLT) projects, including:* Automatic Product Review Summarization* Linguistic Data Transformations (e.g. XLE LFG Parses  Penn Treebank POS Tags)* Semantic Index Evaluation* Syntactic (LFG) Parse-Banking

Us

Multiple HLT and NLP-related projects at a startup targeting semantic search at web scale* Launched (Wikipedia only) May 2008; Acquired by Microsoft September 2008* NLP and infrastructure programming in multiple languages: Ruby, Perl, Java* Diverse management, technical and linguistic responsibilities

Philadelphia, Pa, Us

Managed several projects in Semantic Annotation and Machine Translation resource creation -- covering over 15 languages, including Arabic, Chinese, Bengali and Amazigh.

Coursework Completed Toward Ms, Logic

Ba, Linguistics