Principal Data Scientist, Minecraft at Microsoft

Redmond, Washington, United States -

Full Time

Start Date

Immediate

Expiry Date

08 Apr, 26

Salary

274800.0

Posted On

08 Jan, 26

Experience

10 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Data Science, Machine Learning, AI, Recommender Systems, Search Algorithms, Software Engineering, Representation Learning, Evaluation Methods, MLOps, Real-Time Serving Architectures, NLP, Predictive Modeling, Deep Learning, Reinforcement Learning, Statistical Techniques, Big Data Technologies

Industry

Software Development

Description

Overview At Mojang Studios, the creators of Minecraft, we are on a mission to build a better world through the power of play. Why play? Well, play is at the heart of everything we do. It’s the blocky backbone of our games, the core of our development philosophy, and even the origin of our name. From the relentless experimentation of our endlessly inspiring community to the classrooms where Minecraft has become an essential teaching tool, play is the bedrock of our existence. We enable millions to create and play together, connect people across the globe, and foster a community that is among the most active and passionate in the world. Our community is global and incredibly diverse. When we are developing anything within our franchise, we keep this in mind. We want everyone to not only feel included in Minecraft, but also to see themselves in what we make. Our goal is for the Mojang Studios team to be as diverse as our community. The Principal Personalization Data Scientist at Mojang Studios will lead the technical strategy, development, and execution of AI-driven personalization products and capabilities both inside and outside the game. This role leverages expertise in AI and ML algorithms, frameworks, and architectures to connect players with content they love. It is a key position in delivering our AI strategy to make Minecraft feel more personal and engaging. The Prinicpal Data Scientist will have experience working in fast-paced, innovative environments and a proven track record of delivering high-quality products to production. They should possess deep expertise in recommender-system algorithms and architectures, including collaborative filtering, matrix factorization, graph-based methods, deep-learning rankers, contextual bandits, and reinforcement-learning approaches. An understanding of representation learning is essential, particularly in areas such as user and item embeddings, sequence models, transformer-based architectures, and two-tower models. Additionally, the Principal Data Scientist should have a solid grounding in search fundamentals, including indexing, retrieval, relevance modeling, ranking, and hybrid search techniques that combine vector and keyword approaches. Expertise in evaluation methods is critical, encompassing offline metrics like NDCG (Normalized Discounted Cumulative Gain), MAP (Mean Average Precision), and recall@K as well as validation strategies and the design and analysis of online experiments such as A/B tests, guardrails, and statistical significance. The Principal Data Scientist will demonstrate software engineering fundamentals and the ability to write production-quality code using modern development practices, including GitHub workflows, CI/CD (Continuous Integration and Continuous Delivery) pipelines, and code reviews. In the end, it’s the people of Mojang Studios that make this place truly special. When you join, you’ll find yourself in the company of incredibly bright, warm, and creative individuals – all united and working toward a single goal. Come help us reach it! Responsibilities Design and implement large-scale Search and Personalization systems—including real-timerecommendations, ranking, and re-ranking—that are simple, extensible, maintainable, and well-documented. Lead design, implementation, and code reviews across Search and Personalization services (candidategeneration, ranking, re-ranking, real-time features) to ensure consistency, performance, reliability, and technical excellence. Scale personalization and search systems to support a massive global player base and a rapidly growingcontent catalogue, ensuring high availability, low latency, and predictable performance under heavy load. Continuously improve existing pipelines (data ingestion, feature engineering, model training/inference,indexing, retrieval) to reduce latency, increase relevance, and elevate overall player experience. ·Maintain robust automated testing and evaluation frameworks, including unit/functional tests, offline relevance metrics, and online A/B experiments with clear guardrails, success criteria, and regression monitoring. Drive player-centric quality and usability by instrumenting telemetry, monitoring model and search behavior in production (drift, bias, safety, query performance), and iterating based on player outcomes and feedback. Act as DRI (Designated Response Individual) /ICM (Directly Responsible Individual) during incidents and high-urgency events, ensuring timely triage, root-cause identification, communication with stakeholders, and stabilization of Search and Personalization systems. Qualifications Required Qualifications: Doctorate in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 5+ years data-science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR Master's Degree in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 7+ years data-science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR Bachelor's Degree in Data Science, Mathematics, Statistics, Econometrics, Economics, Operations Research, Computer Science, or related field AND 10+ years data science experience (e.g., managing structured and unstructured data, applying statistical techniques and reporting results) OR equivalent experience. Preferred Qualifications: Experience in AI/ML (Artifical Intelligence/Machine Learning) principles, frameworks, and tools (e.g., Generative AI, RAG (Retrieval-Augmented Generation) with experience in big-data technologies like Spark (PySpark) and Databricks. Expertise in recommender systems and search algorithms and architectures: collaborative filtering,matrix factorization, graph-based methods, deep-learning rankers, contextual bandits, reinforcement-learningapproaches, indexing, retrieval, relevance modeling, ranking, and hybrid search (vector + keyword) Software-engineering fundamentals and ability to write production-quality code using modern development practices (GitHub, CI/CD, code reviews). Understanding of representation learning: user/item embeddings, sequence models, transformer-based architectures, and two-tower models. Expertise in evaluation methods: offline metrics (NDCG, MAP, recall@K, coverage, diversity), validation strategies, and designing/analyzing online experiments (A/B tests, guardrails, statistical significance). Skilled in MLOps (Machine Learning Operations) practices: CI/CD for ML, feature stores, model-training pipelines, deployment workflows,and monitoring for latency, drift, bias, and performance. Expertise in real-time serving architectures: low-latency APIs, distributed serving systems, caching strategies,vector databases, and scalable cloud infrastructure. Experience designing, deploying, and monitoring large-scale ML and personalization systems in production. Familiarity with multiple ML domains: NLP (Natural Language Processing), predictive modeling, time-series forecasting, deep learning, and reinforcement learning. Games-industry knowledge. Verbal and written communication skills; ability to translate complex technical concepts to non-technical stakeholders. Applied Sciences IC5 - The typical base pay range for this role across the U.S. is USD $139,900 - $274,800 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $188,000 - $304,200 per year. Certain roles may be eligible for benefits and other compensation. Find additional benefits and pay information here: https://careers.microsoft.com/us/en/us-corporate-pay This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled. Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.

Responsibilities

Design and implement large-scale Search and Personalization systems, ensuring high availability and performance. Continuously improve existing pipelines and drive player-centric quality and usability.