Generative AI Engineer

FabFitFun is seeking a Generative AI Engineer to join our Engineering team! Reporting to our Senior Manager, Engineering, this person will have the exciting opportunity to help leverage AI technology within our FFF ecosystem. 

Location: FabFitFun is based in Beverly Hills, CA. This position is eligible to work hybrid from our HQ (preferred) or is eligible for remote. 

What You’ll Do:

Project Leadership

• Lead the development of generative AI solutions from the ground up, including strategic planning and technical execution.
• Act as a thought leader to align the chatbot's capabilities with company goals and provide recommendations for best practices.

Technical Development

• Design and implement customer-facing chat experiences integrated into our platforms, including features such as:
•  Personalized product descriptions.
• Customer-facing chatbots to improve user engagement, including features that enable users to manage their account, billing, purchasing, and order status.
• Agents for managing complex internal workflows.
• Develop, optimize, and maintain backend and application code in Python and Java to support chatbot functionalities.
• Craft and fine-tune effective prompts for generative AI use cases, iteratively improving quality by conducting experiments.
• Deploy and manage chatbot components in production, ensuring their stability, scalability, and performance.

Quality Assurance

• Develop or procure a comprehensive solution to validate and monitor the quality of chat interactions, ensuring the chatbot meets performance, reliability, and user experience standards.

Collaboration & Process

• Collaborate with cross-functional teams to define requirements and align project goals.
• Participate in weekly sprints to ensure timely planning, execution, and review of tasks.
• Establish standards and best practices through comprehensive documentation and training.

What You’ll Bring:

• 1 year of experience working with foundational LLM models, including deploying, fine-tuning, and integrating these models into production environments.
• 5 years of experience as a software engineer with a strong focus on backend development.
• Proficiency in Python or Java.
• Understanding of data science concepts to support performance evaluation.
• Designed, built, and operated domain-driven backend systems at scale.
• Worked in agile environments, including kanban and hybrid systems.
• Simplified complex technical concepts for non-technical stakeholders and curious teammates.
• Automated systems for long-term, stable production operation with minimal human intervention.
• Driven continuous delivery, ensuring small and frequent deployments.
• Tuned observability across the stack to enhance monitoring and reliability.
• Worked on prompt engineering, experimenting with different approaches to enhance AI output.

Preferred AI Experience

• Deployed and integrated AI models, specifically LLM foundational models, into real-world applications.
• Worked with LLM agent architectures like AutoGen, MetaGPT, CrewAI, LangGraph, Semantic Kernel, AutoGPT, and Swarm.
• Developed or worked with traditional chatbot frameworks such as Dialog Flow, Rasa, Microsoft Bot Framework, and Wit.ai.
• Fine-tuned large language models to improve application-specific performance.
• Implemented AI safety practices and guardrails to ensure ethical and responsible AI usage.

The expected base salary range for this position is $150K to $190K bonus. The compensation package will also include an initial equity grant, in addition to a range of generous medical, dental, vision and other perks & benefits. The compensation package will also include an initial equity grant, in addition to a range of generous medical, dental, vision and other perks & benefits. Compensation decisions are determined using a variety of job-related factors such as skill set, geographic location, market demands, experience, and education / certifications. If we extend an offer for employment, we will consider all individual qualifications.