Staff/Lead Data Scientist - NLP in London

Proofpoint is looking for a Lead/Staff Data Scientist to join our Algo team. The key responsibility for this role is to further enhance our email threat detection engine that protects some of the largest businesses in the world. You will collaborate cross‑org with Product and Engineering and lead major initiatives end‑to‑end ensuring that we apply state‑of‑the‑art machine learning tools and techniques to identify and solve the most impactful problems. You will also help promote machine learning best practices and encourage new approaches to problem‑solving within the team.

Your day‑to‑day:

• Wrangle and draw insights from massive amounts of unstructured textual data (email datasets) using the latest tools and technologies like Spark, Iceberg, Athena, AWS SageMaker.
• Apply state‑of‑the‑art machine learning techniques like encoder‑decoder transformers, LLMs, Graph Neural Networks to solve some of the most challenging problems.
• Directly impact the effectiveness of our core products by training and deploying models to production using AWS SageMaker as the MLOps platform.
• Apply unsupervised learning algorithms across billions of email interactions to identify emerging threat patterns.
• Collaborate, communicate, and partner with Product and Engineering teams promoting a data‑driven approach to identify focus areas for data science.
• Mentor data scientists, drive best practices and cultivate an environment of experimentation and learning.
• Stay up‑to‑date with the latest advancements in machine learning, AI technologies, and incorporate them into our solutions where applicable.

What you bring to the team:

Essential:

• Experience leading multiple highly impactful machine learning projects with proven results.
• Hands‑on experience in the NLP domain involving training, fine‑tuning and productionising transformer‑based models for text classification / text‑embeddings (experience with LLMs, generative AI is a plus).
• Experience monitoring and maintaining performance of models over time in production taking into account model/data drifts.
• In‑depth experience with one or more deep neural network frameworks (e.g. PyTorch, Tensorflow, JAX).
• A creative mindset, propensity to care deeply about the impact their team has and to encourage novel ways of critical thinking in their team.
• Excellent listening skills; open to input from other team members and departments.

Optional:

• Conceptual understanding of Graph Neural Networks and experience applying GNNs to solve real world problem statements will be a plus.
• Experience working on large imbalanced datasets, evaluating and selecting models that work well in production on imbalanced real‑world data.

Why Proofpoint:

Protecting people is at the heart of our award‑winning cybersecurity solutions, and the people who work here are the key to our success. We’re a customer‑focused and driven‑to‑win organisation with leading‑edge products. We are an inclusive, diverse, multinational company that believes in culture fit, but more importantly ‘culture‑add’, and we strongly encourage people from all walks of life to apply. We believe in hiring the best and the brightest to help cultivate our culture of collaboration and appreciation. Apply today and explore your future at Proofpoint!