We are looking for a Research Engineer (Model Personality) who can lead the development of personality-aligned behaviors in AI models, blending human nuance with machine intelligence. This is a hybrid role that fuses technical research, prompt engineering, and behavioral design—perfect for someone who sees language as both science and soul.

What You’ll Do

• Design and refine personality frameworks for AI models to ensure consistency, tone, and alignment across interactions.
• Develop, test, and optimize prompts, conditioning strategies, and fine-tuning data that drive desired behaviors.
• Collaborate with NLP researchers, linguists, and product teams to shape emotional intelligence, style, and ethical boundaries.
• Evaluate model outputs through both qualitative and quantitative lenses, iterating on behavior to match human expectations.
• Build tools or pipelines to automate and analyze prompt performance, tone drift, or persona inconsistencies.
• Conduct experiments around persona modulation, few-shot tuning, and instruction optimization.
• Stay on the bleeding edge of alignment, LLM steering, and human-AI interaction techniques.

Skills We’re Looking For

• Strong foundation in NLP, machine learning, or computational linguistics.
• Proficiency in Python and common ML libraries (e.g., PyTorch, TensorFlow, HuggingFace Transformers).
• Experience with prompt engineering and large language models (LLMs).
• Deep sensitivity to tone, nuance, emotional resonance, and human communication patterns.
• Familiarity with evaluation techniques for model behavior and alignment.
• Ability to write, edit, and assess text creatively and analytically.
• Excellent collaboration skills and comfort in experimental, research-driven environments.

We’d Love It If You’ve Had

• Prior experience working directly with LLMs in production or research settings.