ML/Research Engineer, Safeguards

This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.

Company Overview

A leading AI research and technology organization is focused on developing reliable, interpretable, and steerable artificial intelligence systems designed to be safe and beneficial for users and society. Its multidisciplinary team brings together researchers, engineers, policy experts, and business leaders to develop and deploy advanced AI systems responsibly.

The organization is seeking ML Engineers and Research Engineers to help detect and mitigate misuse of AI systems. As part of the Safeguards ML team, the role will focus on developing systems that identify harmful use, ranging from individual policy violations to sophisticated and coordinated attacks, while creating defenses that adapt as AI capabilities advance.

The role will also contribute to systems designed to protect user wellbeing and ensure AI models behave appropriately across a broad range of contexts. This work supports responsible AI development and safety commitments.

Key Responsibilities

• Develop machine learning classifiers to detect misuse and anomalous behavior at scale.
• Build synthetic data pipelines for training classifiers and develop methods for automatically sourcing representative evaluations.
• Develop systems that monitor harms spanning multiple interactions and exchanges, including coordinated cyber attacks and influence operations.
• Create methods for aggregating and analyzing signals across different contexts and interactions.
• Evaluate and improve the safety of agentic AI products.
• Develop threat models and testing environments to identify and assess risks associated with agentic systems.
• Develop and deploy mitigations for prompt injection attacks.
• Conduct research into automated red-teaming and adversarial robustness.
• Explore research methods that help identify, evaluate, and mitigate potential misuse of AI systems.
• Work across the research-to-deployment pipeline, translating exploratory research into reliable production systems.
• Collaborate with researchers, engineers, and other stakeholders to develop scalable AI safety solutions.

Required Qualifications

• 4+ years of experience in machine learning engineering, research engineering, or applied research in academia or industry.
• Proficiency in Python.
• Experience building and deploying machine learning systems.
• Ability to work across the research-to-production pipeline, from exploratory experiments to production systems.
• Strong interest in identifying and mitigating AI misuse risks.
• Strong written and verbal communication skills.
• Ability to explain complex technical concepts clearly to non-technical stakeholders.
• Strong problem-solving and research skills.
• Ability to collaborate effectively across multidisciplinary teams.

Preferred Qualifications

• Experience with language modeling and transformer-based architectures.
• Experience building classifiers, anomaly detection systems, or behavioral machine learning systems.
• Experience with adversarial machine learning or red-teaming.
• Experience with interpretability techniques or model probes.
• Experience with reinforcement learning.
• Experience developing high-performance, large-scale machine learning systems.
• Experience researching AI safety, security, misuse detection, or related areas.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

1.No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.

2.No Client Relationship: This company is not a client of SpringCube unless stated.

3.To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.

4.No Liability: SpringCube is not liable for inaccuracies.**