Principal Research Engineer, Post-Training
Redwood City, CA$275k - $400kFull-timePosted 4mo ago
About the role
Role leading post-training systems for transforming foundation models into aligned, engaging products. Focus on post-training of OSS LLMs to power Character.AI’s immersive chat features; cross-functional leadership spanning data, algorithms, infrastructure, and evaluation to improve model performance and user experience.
Responsibilities
- Technical Leadership & Mentorship: Define and drive the technical roadmap for mid- and post-training systems, mentoring a team of researchers and engineers, and establishing best practices for experimentation, model development, and deployment.
- Research & Model Development: Lead alignment algorithms, optimization techniques, and training objectives; advance mid- and post-training methods including reinforcement learning, preference optimization, supervised fine-tuning, and emerging alignment approaches; develop robust evaluation frameworks and quality signals.
- Systems & Infrastructure: Design efficient training and inference systems for large-scale generative models; architect scalable data pipelines; optimize distributed training, GPU utilization, and serving efficiency; improve experimentation platforms, data quality systems, and model observability.
Qualifications
- PhD in Computer Science, Machine Learning, AI, or a related field, or equivalent industry experience.
- Significant experience leading technical projects or teams in ML, AI research, or large-scale distributed systems; experience scaling and mentoring teams.
- Deep understanding of modern ML techniques including transformers, reinforcement learning, alignment methods, and LLMs.
- Track record of delivering impactful research or applied ML systems in production.
- Expertise in designing, building, and maintaining production-quality ML systems and infrastructure.
- Experience training, serving, debugging, and optimizing large-scale models on GPU-based systems.
- Experience leading teams in LLM training, mid-training, or post-training.
- Experience with product experimentation, online evaluation, and A/B testing frameworks.
- Strong software engineering skills and ability to write clean, scalable code.
- Excellent communication skills and ability to influence across teams.
Skills
Required:Technical leadershipAlignment algorithmsReinforcement learning
Nice to have:Supervised fine-tuning
Benefits
- Top-notch health coverage for you & your family, majority covered
- Generous 401(K) contribution
- Paid leave up to 20 weeks for new parents
- 4 weeks of PTO
- Daily in-office catering plus monthly Doordash stipend
- Monthly wellness stipend
Last updated Jul 15, 2026. Interested? Apply on the company site.
About Character.AI
AI Chat, Reimagined–Your Words. Your World.
Chat with millions of AI Characters on the #1 AI chat app. Where will your next adventure take you?
AI ChatCharactersliquid-ai-recruiting-target
More open roles at Character.AI
- Technical Program Manager, Product Experience3mo agoRedwood City, CA · Product
- Technical Program Manager, Model Alignment and Deployment4mo agoRedwood City, CA · Safety
- Technical Program Manager, AI Infrastructure6mo agoHybrid (Redwood City, CA) · Safety
- Staff Data Scientist, Monetization9mo agoHybrid (Redwood City, CA), Hybrid (New York, NY) · Product
- Software Engineer, Backend/Applied ML (Safety & Integrity)9mo agoHybrid (Redwood City, CA) · Technical Staff - Engineering