Joblaze summary

In the role of Researcher on Cartesia's Post-Training team, the individual will focus on developing innovative techniques for optimizing model preferences and evaluating performance across multimodal systems. Key skills include a strong background in preference optimization methods, experience with generative models, and the ability to build and scale complex machine learning infrastructures. This position is well-suited for someone with a solid foundation in machine learning research and engineering, particularly those interested in advancing AI alignment and human interaction. Cartesia's collaborative environment emphasizes rapid execution and a commitment to quality in cutting-edge AI dev

Joblaze insights

Listed about a month ago — first seen on Joblaze September 3, 2026. Last confirmed on Cartesia's careers page October 27, 2026.
Machine Learning appears in 10.4% of 481 comparable mid ai/ml roles in United States.

Quick facts

Is the Researcher, Post Training role remote?: No — this is an on-site role in *HQ - San Francisco, CA.
Where is the role based?: Cartesia is hiring for this position in *HQ - San Francisco, CA.
What's the tech stack?: Joblaze extracted these technologies from the posting: Machine Learning, Multimodal Models, RLHF, alignment methods, preference optimization.
Does Cartesia sponsor work visas for this role?: Yes — the posting indicates visa sponsorship is available for the right candidate.
What seniority level is this role?: Cartesia targets mid-level candidates for this position.
Is this full-time or contract?: Full-time for this Researcher, Post Training role at Cartesia.

From the original posting

About the Role

The next leap in model intelligence won’t come from scale alone — it will come from better post-training and alignment. Cartesia’s Post-Training team is developing the methods and systems that make multimodal models truly adaptive, aligned, and grounded in human intent.

As a Researcher on the Post-Training team, you’ll work at the intersection of machine learning research, alignment, and infrastructure, designing new techniques for preference optimization, model evaluation, and feedback-driven learning. You’ll explore how feedback signals can guide models to reason more effectively across modalities, and you’ll build the infrastructure to measure and improve these behaviors at scale.

Your work will directly shape how Cartesia’s foundation models learn, improve, and ultimately connect with people.

Your Impact

Own research initiatives to improve the alignment and capabilities of multimodal models
Develop new post-training methods and evaluation frameworks to measure model improvement
Partner closely with research, product, and platform teams to define best practices for creating specialized models
Implement, debug, and scale experimental systems to ensure reliability and reproducibility across training runs
Translate research findings into production-ready systems that enhance model reasoning, consistency, and human alignment

What You Bring

Deep knowledge of preference optimization and alignment methods, including RLHF and related approaches
Experience designing evaluations and metrics for generative or multimodal models
Strong engineering and debugging skills, with experience building or scaling complex ML systems
Ability to trace and diagnose complex behaviors in model performance across the training and evaluation pipeline

Nice-To-Haves

Experience with multimodal model training (e.g., text, audio, or vision-language models)
Contributions to alignment research or open-source projects related to model evaluation or fine-tuning
Background in designing or implementing human-in-the-loop evaluation systems

🏦 401(k)

🦖 Your own personal Yoshi

Standard company text repeated across Cartesia's postings is omitted here.

Researcher, Post Training

About the Role

Your Impact

What You Bring

Nice-To-Haves

Similar positions