Team & Role Overview:
The Responsible AI team at LinkedIn serves as the centralized hub of excellence for AI and Data Science, spearheading the technical and organizational strategy to ensure trust, compliance, and safety for all LinkedIn members and clients. We ensure LinkedIn鈥檚 AI solutions are aligned with principles of Fairness, Inclusion, Transparency, and now, advanced post-training LLM alignment work. Our work involves fine-tuning and aligning large language models with LinkedIn鈥檚 core principles, focusing on critical areas such as privacy, fairness, explainability, safety, hallucination reduction, and robustness.
This team drives applied research and the development of scalable, industry-leading solutions across LinkedIn's AI platforms, models, and products.
Location:
At LinkedIn, our approach to flexible work is centered on trust and optimized for culture, connection, clarity, and the evolving needs of our business. The work location of this role is hybrid, meaning it will be performed both from home and from a LinkedIn office on select days, as determined by the business needs of the team.
This role will be based in Sunnyvale, CA
Responsibilities:
Conduct independent, hands-on research into the state-of-the-art in differential privacy, secure computation, and privacy-preserving machine learning.
Evaluate, adapt, and implement advanced algorithmic approaches to optimize for data utility and privacy guarantees in production environments.
Establish and manage rigorous evaluation frameworks to quantify the fidelity, utility, and privacy guarantees of generated and anonymized data.
Partner with cross-functional teams of data scientists, software engineers, product managers, and governance specialists to ensure the seamless integration and adoption of new privacy capabilities across the enterprise.
Develop privacy-first training algorithms and techniques
Develop evaluation and auditing techniques to measure the privacy of training algorithms
Design and prototype privacy-preserving machine-learning algorithms (e.g., differential privacy, secure aggregation, federated learning) that can be deployed at enterprise scale.
Measure and strengthen model robustness against privacy attacks such as membership inference, model inversion, and data memorization leaks鈥攂alancing utility with provable guarantees.
Develop internal libraries, evaluation suites, and documentation that make cutting-edge privacy techniques accessible to engineering and research teams.
Lead deep-dive investigations into the privacy鈥損erformance trade-offs of large models, publishing insights that inform model-training and product-safety decisions.
Define and codify privacy standards, threat models, and audit procedures that guide the entire ML lifecycle鈥攆rom dataset curation to post-deployment monitoring.
Collaborate across Security, Policy, Product, and Legal to translate evolving regulatory requirements into practical technical safeguards and tooling.
Provide technical leadership and mentorship to a team of engineers, fostering a culture of innovation and excellence.