Staff Machine Learning Engineer - Thorn

At Thorn, our cause is our code. We are a nonprofit whose mission of defending children from sexual exploitation and abuse is deeply embedded within our core—a shared code that drives us to do challenging work with resilience and determination.

Here, you’ll work and grow among the best hearts and the best minds in tech, data, and business alongside our network of independent partners, NGOs, and law enforcement agencies. Together, we’re focused on building technology that protects children’s futures. We are looking for dynamic problem solvers with the desire to help address some of today’s toughest issues. You'll collaborate with a diverse group of peers in a remote environment centered on wellness, care, and compassion.

About the Role

As a Staff ML Engineer at Thorn, you will design, build, deploy, and maintain world-class models, classifiers, and algorithms to increase Thorn’s capabilities to achieve our mission of the elimination of child sexual exploitation. You will be the go-to expert in one or more domains of machine learning and provide critical guidance to multiple teams across legal, engineering, product, business development, and external affairs. You will directly contribute to building automated solutions that:

1. Reduce the time it takes to identify a child sexual abuse victim, elevating the most vulnerable and high-risk victims from an ocean of online content.
2. Enable the removal of child sexual abuse material from the internet, finding known and new content.
3. Prevent online abuse from happening in the first place, detecting abusive content before it spreads.

You are responsible for ensuring your work is high quality and for mentoring other ML Engineers. You will thrive in highly ambiguous problem spaces and creatively design and build scalable solutions with minimum direction, navigating legal, product, and technical constraints.

What You’ll Do

• Own end-to-end model development: design, build, test, and maintain machine learning systems and algorithms.
• Lead machine learning system designs, set engineering standards, lead technical meetings, and proactively engage and mentor other engineers.
• Help debug, conduct code reviews, and support general machine learning initiatives across the team.
• Define data sourcing and labeling strategies for your technical domain, partnering with the Sr. Technical Program Manager to drive planning and prioritization.
• Work closely with specialists to create data labeling guides and support labeling efforts (which may involve engaging with sexually explicit material that is not child sexual abuse material).
• Streamline and reuse work, proactively identifying cross-team dependencies, anticipating technical risks, defining architectural guardrails, and establishing best practices for scalability and reliability.
• Represent Thorn as a technical thought leader at conferences and other external forums.
• Collaborate with engineers, product managers, product owners, and designers to drive requirements, define scope, and translate user needs into deliverables.
• Collaborate with product engineers to maintain and deploy models, algorithms, and model serving infrastructure.
• Improve the innovation-to-impact cycle across product, academic collaborations, and other external partnerships.
• Build relationships and author tools, policies, and patterns that raise productivity for the Machine Learning team.
• Clearly communicate and document problem formulation, feature/model design, training, and evaluation results to technical and non-technical audiences.
• Drive roadmap planning and cadence of maintenance versus new feature development for your areas of ownership.

What We’re Looking For

• Commitment to putting the children we serve at the center of everything you do.
• Willingness to learn about online child safety and victim identification.
• 8+ years background in machine learning and/or artificial intelligence, with 3+ years of experience building production-scale computer vision and/or NLP machine learning systems and pipelines.
• Ph.D. or Master’s degree in a quantitative field, or equivalent professional experience.
• Demonstrated ability and interest in learning and adopting new technologies quickly.
• Comfort working through ambiguity, shifting requirements, and collaborating with cross-functional stakeholders.
• High empathy, curiosity, humility, and willingness to both teach and learn.
• Clear, efficient, and thoughtful written and verbal communication skills in a distributed environment.

Technologies We Use

• AWS
• Python, Pandas, scikit-learn, scipy
• PyTorch, TensorFlow with Keras
• Hugging Face Transformers & Diffusers
• OpenCV, FAISS (and other vector stores), ONNX/onnxruntime
• Terraform, CI/CD Pipelines, Kubernetes

Work Model & Travel

Our remote-first work model is structured around working from home most of the time. There will be times when employees are expected to travel, such as company-wide gatherings, team offsites, or industry conferences.