Senior Machine Learning Engineer / Data Scientist – Real-time Ad Targeting and Automated Bidding Offline

A full-time Machine Learning Engineer / Senior Data Scientist position for an exceptional candidate who has a keen interest in applying AI systems at scale. You will be designing and building machine learning systems that

will operate on real-world data making decisions in real-time. You will be working in the highly exciting area of real-time ad targeting. The work involves handling billions of records of ad-serving requests.

LoopMe has a significant investment in AI. We are interested in pushing the boundaries and staying ahead of the competition rather than reapplying tired old systems. We do this by developing genuinely new AI systems and applying it in exciting and novel ways, please see our publications in the About the Data Science Team section below. (The second won the best paper at adKDD 2021.)

This is a rare opportunity to be involved in creating an automated system to optimize thousands of real-time bidding interactions per second with online customers, and to quantify the benefits created against control groups

in a live environment. It is also an opportunity to become part of a high-growth, UK tech start-up and get first-hand experience in how tech start-ups operate.

The work involves analyzing billions of records of ad-serving opportunities, ad-serves, and ad-server responses to understand what factors explain the variance in the expected response value.

Key Skills & Experience:

A minimum of a Bachelor’s degree in a mathematical discipline such as Computer Science, Applied Statistics, Maths, Engineering or Physics from a respected University. A PhD is a bonus

- 3+ years experience of Python and good solid knowledge of R

- At least 4 years practical experience of univariate and multivariate statistical analysis in Python or R with large data sets (millions of records and many tens or hundreds of independent variables)

- Good experience of variable transformation and data preprocessing techniques to extract maximum predictive power such as binning, piecewise linear regression, non-linear function transforms, etc.

- Excellent practical knowledge of multi-variate techniques such as: XGBoost, Logistic Regression, Decision Trees, Random Forest, Naive Bayes, Clustering, etc. and a good grasp of the strengths and weaknesses of specific approaches

- Strong communication skills

Key Responsibilities:

You will report to the Chief Data Scientist and join a team of 15

other senior data scientists and data engineers. See About the Data Science Team section below to check out who we are. You will help to solve tough (but never dull) problems, such as:

- Developing new real-time bidding algorithms

- Prototyping real-time machine learning algorithms using cutting edge research

- Developing applications to visualize and manipulate huge amounts of data

- Analysis of new data streams for inclusion in our real-time ad targeting engine

- Scaling systems to handle many terabytes of data whilst still maintaining millisecond-level response times

- Working to support the following steps in the analytical process with large (multi-million record) datasets:

- Basic data cleansing and preparation

- Variable preprocessing/transformation

- Performing statistical tests

- Generation of graphical output

- Preparation of data sets for predictive modeling

- Robust predictive model building, validation, and application

- Automation of statistical processes

We are a small, highly interactive team working in an Agile environment. You will need strong communication skills. You will also be expected to care deeply about the quality of your code: its clarity, documentation, and

testing.

Bonus Qualifications:

- Experience of real-time bidding and auction theory

- Proficient in Java or similar language

- Experience of scrum / agile software development

- Experience of managing small teams

- Practical knowledge of infrastructure for running high availability systems. (Airflow, ElasticSearch, Kafka, ClickHouse, Spark, etc.)

About you:

- Demonstrates a high level of initiative

- Has an enquiring mind and a disciplined scientific approach to extracting facts and understanding observed behavior

- Are excited by the potential of analytical intelligence to realize high-value commercial outcomes and change the way that business operates

- Consistently delivers high-quality answers

- Want to be part of a high growth start-up company with global ambitions

About the Data Science Team:

- We are a team of 15 data scientists and data engineers building systems to apply the latest AI methods and research to real-world problems. LoopMe has over 200 employees, 100 of which are technical.

- We are a distributed team with offices in both London and Ukraine.

- We are open to new ideas and actively strive to improve both our systems and our development practices. It is a team where anyone can have a real impact.

- We are an inclusive and welcoming team in which people enjoy working with their colleagues and feel

valued.

- We occasionally publish papers that may give a flavor of our work in automated bidding, for example:

-Gradient Boosting Censored Regression for Winning Price Prediction in Real-Time Bidding, P Paliwal, O Renov, International Conference on Database Systems for Advanced Applications 2019

-Hybrid Dual Censored Joint Learning of Reserve Prices and Bids for Upstream Auctioneers, P Paliwal, L Stavrogiannis, ADKDD 2021 (won best paper) http://papers.adkdd.org/2021/papers/adkdd21-paliwal-hybrid.pdf

- The team is led by an experienced Chief Data Scientist Leonard Newnham

Benefits:

- Competitive compensation package

- Hundreds of millions of people see your work and use our products worldwide

- A transparent work environment

- Working in a team that inspires, and works with you to achieve industry-changing goals