Senior Research Scientist - Phish and Spam Detection

Yahoo Mail is the ultimate consumer inbox with hundreds of millions of users. It's the best way to access your email and stay organized from a computer, phone or tablet. With its beautiful design and lightning fast speed, Yahoo Mail makes reading, organizing, and sending emails easier than ever.

The Mail Intelligence platform is responsible for building the next generation platforms and services enabling Yahoo to deliver deeply personalized content to the hundreds of millions of users wherever they are and whatever mode of consumption they are using.

We (Mail Intelligence platform) process billions of mail messages (data in tune of several petabytes). With the help of cutting edge algorithms we extract information, build knowledge, interconnect information between different sources to deliver a great experience to our users. Building this knowledge provides many challenges in the areas of natural language processing, machine learning techniques, big data processing in order of petabytes.

You will build tools and workflows to make it easier to manage and act on this vast information. You will apply your insights on the data to build innovative consumer applications for Yahoo.

Yahoo Mail is the ultimate consumer inbox. It is the best way to access your email and stay organized from a computer, phone or tablet. With its beautiful design and lightning fast speed, Yahoo Mail makes reading, organizing, and sending emails easier than ever. Come join this amazing team of Engineers, Product Managers and Designers to work on next generation innovative experiences transforming how users connect with each other every day.

• You are an expert in developing and applying state-of-the-art machine learning and deep learning models to solve complex problems.
• You thrive in a research-oriented environment and enjoy pushing the boundaries of innovation to deliver impactful solutions.
• You have a strong academic foundation and are passionate about the domains of phishing/spam detection using machine learning in large-scale systems.
• You excel in transforming theoretical research into practical applications, preferably in the domains of phishing and spam detection, classification tasks, and Natural Language Processing (NLP).
• You are a hands‑on expert with experience in training and evaluating large‑scale models, including cutting‑edge deep learning architectures.
• You have a collaborative mindset, excellent communication skills, and the ability to contribute to a high‑performing team in a fast‑paced environment.

• Conduct research to develop and advance innovative algorithms for phishing and spam detection tailored to large‑scale email inboxes.
• Design, train, evaluate, and optimize state‑of‑the‑art ML models for anti‑phishing and anti‑spam classification, including transformer‑based models like BERT, RoBERTa, LLM‑driven techniques and knowledge distillation.
• Collaborate with cross‑functional teams to integrate machine learning models into production systems and drive business impact.
• Develop scalable workflows for processing and analyzing large‑scale datasets.
• Stay abreast of the latest research trends and contribute to the team's thought leadership through publications, patents, or presentations.
• Participate in the design and execution of experiments to validate model effectiveness.
• Mentor and guide junior team members in research and development efforts.

• PhD (preferred) or Master's degree in Computer Science, Statistics, Applied Mathematics, or a related field.
• 5+ years of experience in machine learning, deep learning, or related fields, with hands‑on expertise in phishing/spam classification, LLM prompting, distillation, or NLP.
• Strong fundamentals in machine learning and deep learning, with solid expertise in model training and evaluation.
• Comprehensive understanding of deep learning models and architectures, including transformer‑based and generative models.

• Hands‑on experience with Python and frameworks like Tensor Flow or PyTorch.
• Hands‑on experience with Huggingface, Pandas, and Num Py.
• Demonstrated problem‑solving skills and ability to translate complex concepts into actionable solutions.
• Excellent…