Data Scientist II at Media.net

Short Description:

Media.Net, a global ad tech company, is seeking talented individuals to join its dynamic team shaping the future of web products. The company offers a vibrant work environment with comprehensive benefits, emphasizing employee happiness and motivation. The keyword learning team, pivotal in optimizing digital ads globally, tackles challenges using cutting-edge machine learning models. As a Data Science-focused organization, Media.Net addresses complex issues, such as click-through rate prediction and contextual ad matching, employing large-scale distributed computing. Ideal candidates for the role possess a PhD/Research Degree or BS/MS in relevant fields, 3-5 years of experience in ML/AI, and proficiency in Python.

---

 

Position: Data Scientist II/Sr. Data Scientist

Company: Media.net

Location: Bengaluru, Karnataka, India

Job type: Hybrid / Full-time

Life at Media.net:

At Media.Net, we are dedicated to creating a work environment where employees not only love their jobs but also enjoy shaping the future of ad tech. We are fervently committed to recruiting exceptional talent interested in developing the next generation of web products. We firmly believe that the happiness and motivation of our team members are pivotal in achieving our goals.

Our comprehensive benefits package mirrors our company values, encompassing excellent medical care (both physical and mental), life insurance, discounted meals, and even a concierge service.

Media.net workspaces are thoughtfully designed for comfort and collaboration. With open seating plans, conducive to engaging conversations, designated areas for relaxation and indoor activities, and well-stocked pantries, we foster an environment that encourages creativity. Flexible work hours and leaves empower each Media.net team member to tailor their schedules to their roles and responsibilities.

If you are enthusiastic about working in a dynamic, enjoyable, and tech-savvy workspace for a company leading the charge in internet products with a global impact, we look forward to getting to know you!

About Media.net:

Media.net stands as a prominent global ad tech company, dedicated to establishing a transparent and efficient path for advertiser budgets to transform into publisher revenue. Our proprietary contextual technology is at the forefront of advancing Programmatic buying, the industry standard for digital platform ad purchases.

Powering major global publishers and ad-tech businesses across various ad formats, including display, video, mobile, native, and search, the Media.net platform operates on a global scale. With headquarters in New York and a global headquarters in Dubai, we take pride in the value we provide to our 50+ demand and 21K+ publisher partners through innovative products and services.

About the Product:

Media.net facilitates billions of digital ad impressions daily, committed to delivering a superior experience for various digital ad types. The keyword learning team, responsible for optimizing keywords based on URL context, utilizes cutting-edge machine learning models for real-time decision-making. This team manages end-to-end data pipelines, machine learning model development, front API serving, and R&D to ensure accurate and efficient display of optimized keywords.

We continually enhance our engineering solutions for scalability, fault tolerance, automation, and robustness. Statistical techniques and tools are employed to analyze vast amounts of data, enabling the development of scalable machine learning models for intelligent decision-making.

What does the team do?

The team serves as the brain of Media.net's real-time contextual engine, making intelligent decisions on traffic acquisition and ad display at a high scale. Handling millions of unique topics across 5 million domains, the team ensures optimization of displayed ads, addressing challenges like click-through rate and conversion rate prediction, template optimization, and explore/exploit problems. Cutting-edge machine learning and AI technologies on a large Hadoop cluster are employed to achieve these goals.

Data Science is pivotal at Media.net, utilizing advanced statistical and machine learning models, deep learning, and large-scale distributed computing. The team employs tools from mathematics, economics, and auction theory to match users with relevant ads optimally, maximizing revenue for customers and Media.net.

Challenges the team deals with:

1. Using information retrieval and machine learning models to estimate click-through rate and revenue based on slot position, user device, location, and page content for thousands of domains and millions of URLs.
2. Matching ads to page views considering contextual information and designing learning mechanisms for continuous improvement based on user feedback.
3. Addressing sparse data challenges, designing explore-exploit frameworks, and creating fast and scalable learning algorithms.
4. Combining contextual targeting with behavioral user-based targeting.
5. Establishing a unique user identity based on multiple signals for accurate behavioral targeting.
6. Leveraging NLP to identify trends based on page content.

What is in it for you?

• Understand business requirements, analyze and extract relevant information from extensive historical data.
• Apply knowledge of Information retrieval, NLP, Machine Learning (including Deep Learning) to develop prototype solutions with a focus on scale, speed, and accuracy.
• Collaborate with engineering teams to implement prototypes, design model performance metrics, and create reports for tracking.
• Collaborate with engineering teams to identify areas of improvement, develop a research agenda, and execute using cutting-edge algorithms and tools.
• Require a broad understanding of ML algorithms and the ability to apply them to complex practical problems. Strong theoretical background and algorithmic grasp are essential for critical evaluation and creative problem-solving.

Who should apply for this role?

• PhD/Research Degree or BS/MS in Computer Science, Statistics, Artificial Intelligence, Machine Learning, Operations Research, or related field.
• 3-5 years of experience in building Machine Learning/AI/Information Retrieval models.
• Extensive knowledge and practical experience in machine learning, data mining, artificial intelligence, and statistics.
• Understanding of supervised and unsupervised algorithms, including linear models, decision trees, random forests, gradient boosting machines, etc.
• Excellent analytical and problem-solving abilities.
• Good knowledge of scientific programming in Python.
• Experience with Apache Spark is desired.
• Excellent verbal and written communication skills.

Bonus Points:

• Publications or presentations in recognized Machine Learning and Data Mining journals/conferences.
• Knowledge in several areas such as Math/math modeling, decision theory, fuzzy logic, Bayesian techniques, optimization techniques, statistical analysis of data, information retrieval, natural language processing, large-scale data processing, and data mining.
• Ability to deal with ambiguity and break down problems into research problems.
• Strong theoretical and research acumen.
  

Please click here to apply.