Prompt Engineer

About the role

Cantina Labs is a social AI company focused on developing advanced real-time models for storytelling and social interactions. Our flagship product, Cantina, brings characters to life, transforming how people interact and create. As a Prompt Engineer, you'll play a crucial role in shaping how millions of users experience these AI characters.

Responsibilities

• Define and author core behavior system prompts that shape how Cantina bots express personality, emotion, dialect, and social behavior across various media types.
• Create datasets and prompt structures that reliably reproduce key personality traits, making AI personas compelling.
• Prototype new bot traits and product features through prompt engineering and iterate based on qualitative and quantitative evaluation.
• Balance short-term feature development with long-term behavioral consistency and quality across the Cantina ecosystem.
• Collaborate with research to build and maintain behavioral evaluations that measure bot performance, personality fidelity, and interaction quality over time.
• Partner with product, design, and engineering to translate creative intent and user feedback into scalable prompt systems.
• Review, refine, and evolve prompts as they move into production, helping establish best practices and launch criteria.
• Track emerging issues in bot behavior, prioritize improvements, and drive prompt-level solutions in ambiguous or high-impact areas.
• Document model quirks, prompting strategies, and guidelines to scale prompt development across teams.
• Support research and ML in our training efforts by delivering meta-prompts for our synthetic data pipelines and evaluating new model behavior.

Requirements

• 3+ years of experience in prompt engineering and developing LLM-based features end-to-end.
• Strong experience writing, testing, and iterating on complex multi-step and system-level prompts.
• Deep understanding of LLM capabilities, limitations, and quirks, with strong intuition for how input design shapes model behavior.
• Experience creating datasets and evaluating model outputs in collaboration with ML or product teams.
• Strong grounding in psychology, sociology, linguistics, or related fields as they relate to personality, behavior, and dialect.
• Methodical, hypothesis-driven approach to experimentation and iteration.
• Able to manage multiple initiatives, prioritize effectively, and operate independently in ambiguous, fast-moving environments.
• Excellent communication skills, with the ability to explain prompt design decisions to technical and non-technical stakeholders.
• Comfortable communicating with executive-level stakeholders.
• Basic Python familiarity and comfort navigating unfamiliar codebases.

Qualifications

• PhD in Computer Science, Psychology, Linguistics, or a related field.
• Experience with large language models and their applications in AI.
• Knowledge of natural language processing and machine learning principles.
• Experience with prompt engineering and dataset creation.
• Strong analytical and problem-solving skills.

Skills

• Expertise in prompt engineering and LLM-based feature development.
• Strong understanding of psychological and sociological principles relevant to AI character development.
• Ability to work collaboratively with cross-functional teams.
• Proficiency in Python and other relevant programming languages.

Benefits

• Competitive salary and generous company equity.
• Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina.
• 42 days of paid time off, including 15 PTO days, 10 sick days, 15 company holidays, and 2 floating holidays.
• Generous parental leave & fertility support.
• 401(k) retirement savings plan.
• Lifestyle spending account – $500/month to use however you’d like.
• Complimentary lunch and snacks for in-office employees.
• One Medical membership, and more!