Sr. Staff ML Engineer - AI Safety & Education
Insight GlobalAbout the role
JOB DESCRIPTION
About the Role
We’re looking for a Senior Staff Engineer to help lead our efforts in designing, building, and evaluating next-generation safety mechanisms for foundation models.
What You’ll Do
Lead the development of model-level safety defenses to mitigate jailbreaks, prompt injection, and other forms of unsafe or non-compliant outputs
Design and develop evaluation pipelines to detect edge cases, regressions, and emerging vulnerabilities in LLM behavior
Contribute to the design and execution of adversarial testing and red teaming workflows to identify model safety gaps
Support fine-tuning workflows, pre/post-processing logic, and filtering techniques to enforce safety across deployed models
Work with red teamers and researchers to turn emerging threats into testable evaluation cases and measurable risk indicators
Stay current on LLM safety research, jailbreak tactics, and adversarial prompting trends, and help translate those into practical defenses for real-world products
REQUIRED SKILLS AND EXPERIENCE
- 5+ years of experience in machine learning or AI systems, with 2+ years in a technical leadership capacity
- Experience integrating safety interventions into ML deployment workflows (e.g., inference servers, filtering layers, etc.)
- Good understanding of transformer-based models and experience with LLM safety, robustness, or interpretability
- Strong background in evaluating model behavior, especially in adversarial or edge-case scenarios
- Strong communication skills and ability to drive alignment across diverse teams Bachelor’s, Master’s, or PhD in Computer Science, Machine Learning, or a related field
Responsibilities
- Lead the development of model-level safety defenses to mitigate jailbreaks and unsafe outputs
- Design and develop evaluation pipelines to detect edge cases and vulnerabilities in LLM behavior
- Contribute to adversarial testing and red teaming workflows to identify model safety gaps
- Support fine-tuning workflows and filtering techniques to enforce safety across deployed models
- Work with red teamers and researchers to create testable evaluation cases and risk indicators
- Stay current on LLM safety research and translate findings into practical defenses
Qualifications
- 5+ years of experience in machine learning or AI systems
- 2+ years in a technical leadership capacity
- Experience integrating safety interventions into ML deployment workflows
- Good understanding of transformer-based models and LLM safety
- Strong background in evaluating model behavior in adversarial scenarios
- Strong communication skills
Skills mentioned
About Insight Global
Insight Global is an international talent and consulting company that delivers business outcomes in an ever-changing world. We obsess over solving problems and building solutions that move our customers further, faster. With access to top talent in more than 50 countries, our tech-enabled recruiters can build teams quickly. Our technical experts across Cloud, AI, Data, Enterprise Operations, and Applied Engineering deliver solutions tailored to each customer’s needs. As those needs evolve, so do we. As we evolve, though, we stay true to our purpose: to develop people personally, professionally, and financially so they can be the light to the world around them. It shows up in everything we do, from investing in our people to delivering results for our customers to making a meaningful impact in our communities.