Machine Learning Engineer - Trust and Safety

Who We Are  

At Favorited, we are redefining mobile live-streaming as a fully interactive, gamified experience. We’re dedicated to fostering deeper connections between creators and their communities through play, and ensuring that creators are compensated well in the process.  

Our App

• iOS

• Android

About the Role  

The Machine Learning Engineer, Trust & Safety will play a crucial role in developing proactive detection and automation systems to enhance safety on our platform. This position requires expertise in machine learning-based content classification, including experience with third-party solutions like Hive, Anthropic, or similar models. You will work closely with engineers and the Trust & Safety team to build scalable solutions that detect harmful content, automate enforcement, and improve user safety in real time.  

Apply to this position if you:  

• Enjoy solving complex problems and building scalable machine learning systems.  

• Are passionate about creating a safer online environment through AI and automation.  

• Have experience working with Trust & Safety teams to deploy ML-based moderation tools.  

• Are comfortable working in a fast-paced startup environment with shifting priorities.  

• Want to contribute to the development of proactive detection models for harmful content.

• Are excited to work in a real time environment.  

Who You Are 

• Passionate about applying machine learning to real-world safety challenges.  

• Detail-oriented and analytical, with strong problem-solving skills.  

• Excited by the opportunity to take ownership of mission-critical ML systems.  

• A quick learner who thrives in an evolving tech landscape.  

• Comfortable working cross-functionally with engineering, product, and safety teams.  

What You Will Do  

As a Machine Learning Engineer, Trust & Safety at Favorited, you will play a key role in shaping our content moderation and automation systems. Your work will directly impact how we detect harmful content and protect our community.  

• Develop and deploy machine learning models for content classification, abuse detection, and proactive moderation.  

• Implement automated enforcement mechanisms to improve response times and accuracy.  

• Work with third-party ML tools like Hive, Anthropic, or other AI-powered classification models to enhance detection capabilities.  

• Optimize existing Trust & Safety automation pipelines for real-time intervention.  

• Collaborate with engineers and T&S analysts to refine detection thresholds and enforcement logic.  

• Analyze trends in violative content and user behavior to continuously improve detection accuracy.  

• Research and implement state-of-the-art ML techniques for Trust & Safety applications.  

• Improve model performance and scalability to handle high-volume real-time data streams.  

• Work closely with data scientists, backend engineers, and policy teams to ensure ML models align with platform policies and enforcement strategies.  

What We Are Looking For  

We are looking for a skilled Machine Learning Engineer who can build, optimize, and deploy models for Trust & Safety applications. The ideal candidate will have a strong technical background in ML-based classification systems and a passion for online safety.  

Experience & Skills: 

• 3-5+ years of experience in Machine Learning, AI, or Data Science.  

• Hands-on experience with ML-based content classification, ideally using tools like Hive, Anthropic, or similar AI moderation models.  

• Strong programming skills in Python, TensorFlow, PyTorch, or Scikit-learn.  

• Experience working with large-scale datasets and real-time ML inference pipelines.  

• Familiarity with NLP, computer vision, or multi-modal AI models for content moderation.  

• Proficiency in working with cloud-based ML infrastructure (AWS, GCP, or Azure).  

• Understanding of Trust & Safety challenges, online abuse detection, and content moderation policies.  

• Strong problem-solving skills and ability to iterate quickly in a fast-paced environment.  

Bonus Points:  

• Experience working in Trust & Safety, moderation, or anti-fraud ML systems.  

• Knowledge of graph-based ML models or anomaly detection techniques.  

• Experience with real-time ML inference and streaming data processing (Kafka, Spark, etc.).  

• Prior work with ethically-aligned AI moderation tools to reduce bias in ML models.  

• Experience with streaming analytics and optimizing performance of models to be used in near real time and on clients.

Where You’ll Work 

This is a full-time on-site position based in Santa Monica, CA.

Benefits 

• Unlimited PTO to prioritize work-life balance.

• 401(k) plan to help you invest in your future.

• Comprehensive health insurance to support your well-being.

• Paid company holidays for time to recharge.

• Competitive salary that values your expertise and contributions.

At Favorited, we value the creativity and hard work of every team member. Join us as we redefine mobile live-streaming and build a safer, more engaging platform for creators and communities.