Red Spark is a fast-growing digital advertising technology company, recently named by Philadelphia Business Journal as one of Best Places to Work in the Greater Philadelphia area in 2018.
We are looking for a Lead Data Scientist to work cross functionally with our engineering, operations, and product teams.
Our real time bidding infrastructure handles tens of thousands of bid requests every second, and it needs to decide which ad to show for every one of them in real time. Current models include bid price optimization, fraud detection/prevention, click prediction, conversion prediction, fill prediction, and target suggestion. To achieve this, our predictive models need to be not only highly accurate, but also highly scalable.
What You’ll Do:
- You will join a team of talented engineers and data scientists responsible for the machine learning of our real-time ad exchange platform.
- You'll have the unique opportunity to work with petabytes of data generated daily by our systems, analyze/process it with Spark, and build models in Python/Pandas.
- You will perform feature engineering, build new predictive models, and test them on our experimentation infrastructure with the goal of improving ML performance of our current predictors or create entirely new predictors.
- When new models and/or features are ready, you will be able to implement them in our prediction microservice written in GoLang, ensuring that the implementation is tested in terms of performance and code quality.
- You will be responsible for leading the data science team using the agile development process.
- You will work closely with key stakeholders at the company to decompose features into actionable and implementable ML systems.
As our Lead Data Scientist, you'll work on our production systems with high throughput and a high volume of data. Current models include bid price optimization, fraud detection/prevention, click prediction, conversion prediction, fill prediction, and target suggestion.
**Having engineering skills to manage the supporting data infrastructure and embed your algorithms into the production environments is a must!**
What You’ll Need:
- Bachelor’s degree (MS preferred) in Computer Science, Computer Engineering, Statistics, Math, or a related technical field.
- 3+ years of experience working as a data scientist, machine learning engineer, or software engineer.
- Experience leading an agile software engineering team or data science team.
- Extensive experience with Python and Go.
- Extensive experience with Pandas, Numpy, Scipy, and scikit-learn.
- Experience with SQL.
- Experience with Apache Spark.
- Ability to work in a fast-paced environment, adapting to change quickly and often.
- Sound business intuition and strong drive to learn.
- Self-motivated, highly organized, able to coordinate and prioritize parallel tasks.
- Excellent communication skills, able to express complex ideas clearly and concisely.
- Experience with XGBoost a plus.
- Java and C++ experience a plus.
Where You’ll Work:
Our motto at Red Spark is, “love what you do and do what you love.” That’s the spirit you’ll feel in our office every day. Collaboration is essential to how we operate, and we’ve structured our office accordingly. A wide open, modern workspace that’s fully equipped with anything you need from technology to table tennis, our center city Philadelphia office feels even better than home. Check out our space and shots of the team on Instagram.
https://www.instagram.com/helloredspark/
What You’ll Get:
Good work should never go unrewarded. In return for your hard work, we offer all full-time employees 25 days PTO from the get-go, competitive base salaries and dynamic bonus plans, health, dental and vision benefits. Additional perks include music subscriptions, gym membership, catered lunches, and an amazing culture that you’ll have to experience to believe.
by via developer jobs - Stack Overflow
No comments:
Post a Comment