Senior Machine Learning Engineer
San Francisco, CA

Job Description

Hoodline is a media tech company that powers local content creation and discovery across the US. We believe that many of the most exciting and important stories, namely local stories, remain unheard if not untold. We see an opportunity to fill this gap. Using data science and machine learning, Hoodline turns raw data signals into thousands of automated local stories and videos each month. Hoodline's platform also tags and contextualizes content from hundreds of partner publications, adding location and other metadata labels to each story.

Hoodline's APIs and Recommendation Module make it easy for any app or site to integrate with its platform to recommend fresh and relevant content to their users. Partners include ABC, Yahoo Search, MSN, Eventbrite, Uber, CBS, Advance Digital, Zumper and McClatchy, delivering 200M story recommendations per quarter. Investors include Neoteny, Rakuten, Greylock Ventures, Eric Schmidt's Innovation Endeavors, CRV, Social Capital, Sound Ventures, Dentsu, Disney, the Knight Enterprise Fund, 500 Startup, and Softbank VC. We are a passionate team of 25 in the Mission in San Francisco.

About the position

Your primary responsibility will be developing machine learning models for our platform and recommendation engine, and running them at scale to automatically tag incoming partner data and recommend the best experience to our readers. This requires extensive experience with machine learning methods for classification and prediction, along with natural language processing methods for analyzing text and relevant features, including entity recognition, sentiment analysis, and topic categorization.

As a small and growing company, the position would be directly hands on with all aspects of our product, collaborating with and helping to build a world class team working on one of the largest and most challenging problems today-local news and information. If you are curious, driven, eager to take on a unique new challenge, and enjoy identifying practical solutions and applying current tools and methods quickly and effectively to each new problem set, this could be the right home for you.

Responsibilities

* Building and training machine learning models to automatically process and tag incoming content, improving the performance of existing models, and adding new models to identify valuable elements that will improve our products.
* Developing and implementing machine learning models for our content recommendation system, identifying or building relevant features and appropriate algorithms that align with the product and data at hand.
* Designing and conducting experiments and developing metrics to inform the development of these products and subsequent improvements.
* Keeping up with recent advances in recommendation systems, machine learning, and natural language processing.
* Working closely with other team members on the development and support of new products, building models and tools or consulting on the use of machine learning for other aspects of our content automation and distribution.

Requirements

* MSc (PhD preferred) in computer science, machine learning, natural language processing, or a relevant quantitative field
* Experience with commonly available tools and infrastructures for machine learning and natural language processing
* Thorough knowledge of current approaches to machine learning, experience building models for classification and prediction across a range of applied tasks
* Experience developing, deploying, and maintaining recommendation systems in large-scale production environments
* Experience in software development and product development processes (including code design, testing plans, code reviews, and related industry practices)
* Knowledge of Python and machine learning libraries like TensorFlow and Scikit-learn
* 3-5 years of professional experience in the field

Preferred Qualifications

* Passionate about data driven products
* Curiosity about the local content and local news space
* Active participant in meet-ups / groups related to: Machine Learning, Natural Language Processing, Text Mining, Data Analytics, Cloud Computing, Predictive Analytics, etc.
* Experience working with large amounts of user generated content and process data in large-scale environments using Amazon EC2

Perks

* Fun, diverse team
* Catered lunch twice per week
* Unlimited vacation policy
* Friday wine time
* Free gym or commuter credits
* Lots of snacks
* Dog-friendly
* Referral bonus program

Benefits

* Medical, Dental, & Vision Insurance
* Life & Disability Coverage
* 401(k) plan

Investors

Rakuten, Greylock Partners, Social Capital, Graph Ventures, CRV Eric Schmidt's Innovation Endeavors, Pear Ventures, Matter Ventures, John S. & James L. Knight Foundation, and 500 Startups.