Staff Data Scientist

Job Description
Who We Are
Verve has created a more efficient and privacy-focused way to buy and monetize advertising. Verve is an ecosystem of demand and supply technologies fusing data, media, and technology together to deliver results and growth to both advertisers and publishers–no matter the screen or location, no matter who, what, or where a customer is. With 30 offices across the globe and with an eye on servicing forward-thinking advertising customers, Verve's solutions are trusted by more than 90 of the United States' top 100 advertisers, 4,000 publishers globally, and the world's top demand-side platforms. Learn more at

About The Role
In this role you will work closely with product, engineering and other teams, collaborate with other Data Science team and with the Machine Learning Engineers to engineer prototypes into solutions.

Domain
In this role your main focus would be on our Audience generation and insight projects

• Audience generation: ML for embedded targets, audience privacy first approaches, Composite AI agents, etc..
• Audience insight - describe audience composition and characteristics
• Adhoc analysis - support business request to better understand our data assets when data is not readily available from our BI tools
• Support sales pitch - provided valuable extra insight to augment the value proposition for key accounts

Research and Development
Our Data Science role includes the following responsibilities:

• Research and development of cutting edge Machine Learning systems, models, and schemes in many different areas of Adtech
• Develop real-time algorithms for audience creation and segmentation
• Discover insights/patterns in our customers from various data sources such as exchange data, behavioural data, location data, 1 and 3rd party data assets
• Design experiments, oversee A/B testing, evaluate the quality of derived assets and continuously monitor model performance
• Create proof of concepts and data science prototypes
• Search and select appropriate data sets
• Perform statistical analysis and use results to improve models
• Identify differences in data distribution that could affect model performance in real-world situations
• Visualize data for deeper insights
• Analyze the use cases of ML algorithms and ranking them by their success probability
• Understanding when your findings can be applied to business decisions
• Reducing business problems into Machine Learning problems and opportunities
• Verifying data quality

Collaborative Work

• Work closely with product, engineering, and sales teams to drive the use of Data Science across the Verve Group
• Collaborate with our Exchange Data Science team
• Collaborate with Machine Learning Engineers to engineer prototypes into solutions

Job Requirements
What You will bring

• 8+ years experience working as a Data Scientist in industry (preferably in advertising) is a must
• A postgraduate degree in a relevant quantitative field (e.g. applied mathematics, statistics, engineering, computer science, physics, operations research, economics, behavioral sciences). PhD is a strong plus,
• Fluent in statistical analysis, data mining, and machine learning,
• Proficient in Python, SQL, PySpark, TensorFlow (TfLite), Sklearn, Keras and Pytorch
• Enthusiasm for solving interesting problems,
• Willingness to learn and work in a team-oriented and constantly changing environment.

Nice to have
Previous experience in

• Audience creation and insight,
• (Highly imbalanced) classification problems,
• Data asset identification to feature engineering,
• Classification and neural network
• Regularisation, Feature selection, and hyperparameter tuning

What We Also Work With
We work with a wide range of tools, technologies and processes. The right candidate should have willingness to learn new technologies. In this role is you will get hands-on experience with many established and emerging technologies:

• Framework:

• Metaflow (or similar),

• Modeling framework: Tensorflow, Keras, pyTorch
• Hyperparameter tuning framework: HyperOpt, Keras_tuner, ..

• MlFlow,

• Technologies:

• GCP and/or AWS (e.g. logExplorer, Cloud function, Cloud scheduler),

• BigQuery,

• DevOps tooling:

• Airflow (or similar),

• Grafana (or similar),

• Jupyterhub (or similar)

• Other:

• Challenging constraints (Sparse data assets, Privacy first constraints,, low latency for inferences),

• Efficient work with Big Data (wrangling, modeling, low latency inference, shuffling issue),
• Developing data-driven products.

What We Offer

• Be part of a multicultural team that is bringing advertising to the next level
• You will learn and evolve in an empowering environment characterized by entrepreneurial actions
• Responsibility, independence, and an opportunity to participate in projects that have a significant impact on Verve's success
• 3 Wellness days per year (in Q1, Q2 & Q3) and Employee Assistance Program to help you maintain your well-being
• Enhance your professional skills with a yearly training budget and improve your language skills through German and/or English classes
• Work and Travel Program (monthly raffle after 2 years of employment)
• We are eager to build a great team together and we appreciate your help through our Employee Referral Bonus
• Align your interests with the company's success and take part in our Employee Shares Purchase Plan
• You will be entitled to 19 holidays per year in addition to any of the public/bank holidays

• Personalized Benefits Platform; with a budget of 4100 INR/month, you can choose the benefits that fit you best from the following options:

• Mobility and travel

• Entertainment and food

• Fitness and healthcare

• Enjoy food and beverage benefits with colleagues and have fun during team events

• Medical insurance for self and family

Verve provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.