Skip to content
Datology AIDatology AIRedwood City, CA

Research Scientist, Post-Training

Leads research on post-training data curation for foundation models, designing algorithms to generate/improve instruction and preference datasets, and unifying pre/post-training optimization. Requires 3+ years deep learning research, post-training experience with vision/language/multimodal models, and PyTorch proficiency.

180k – 300k
On-site3+ YOEAI Research

About the role

What You'll Work On

  • Post-training data curation: conduct research on algorithmically curating post-training data (e.g., generating/refining preference and instruction-following data, curating capability/domain-specific data, making post-training more effective/controllable/generalizable).
  • Unifying pre-training and post-training data curation: pursue research on end-to-end data curation (curate pre-training data to improve post-trainability, jointly optimize pre/post-training data to maximize final model performance).
  • Transform messy literature into practical improvements: source, vet, implement, and improve promising ideas from literature or your own creation.
  • Conduct science driven by real-world needs: guided by customer needs and product improvements.

About You

Required:

  • 3+ years of deep learning research experience
  • Experience with post-training large vision, language, and multimodal models
  • Post-training algorithm development, data curation, and/or synthetic data methods for:
    • Preference-based tuning (e.g. DPO, RLVR, RRHF)
    • Alternative supervision & self-supervision techniques (e.g. self-training, chain-of-thought distillation)
    • SFT (e.g. instruction tuning, demonstration fine-tuning)
  • Post-training tooling development and engineering experience
  • Strong understanding of deep learning fundamentals
  • Software engineering + deep learning framework (PyTorch or willingness to learn) skills for large-scale experiments and production prototypes
  • Track record of success in deep learning research (papers, tools, artifacts)

Nice-to-haves:

  • Experience with data management and distributed data processing (Spark, Snowflake, etc.)
  • Experience building + shipping ML products

Compensation

  • Base salary: $180,000 - $300,000
  • Significant equity
  • 100% covered health benefits (medical, vision, dental)
  • 401(k) with 4% company match
  • Unlimited PTO
  • Annual $2,000 wellness stipend
  • Annual $1,000 learning stipend
  • Daily lunches/snacks
  • Relocation assistance to Bay Area

Skills

PyTorchDpoRlvrRrhfSftInstruction TuningPreference TuningSynthetic DataData CurationMultimodal Models

Similar roles

AI Research jobs
Datology AI

Research Engineer

Datology AIRedwood City, CA

As a Research Engineer, you will conduct and enable cutting-edge research, translating it into the core product pipeline. You will develop and improve state-of-the-art data curation strategies, accelerating research and ensuring product innovation.

180k – 300k
On-site4+ YOEAI Research
AE Studio

Alignment Scientist/Engineer

AE StudioLos Angeles, CA

Join the alignment research team to work on high-impact, under-resourced projects focused on AI alignment. This role requires strong ML research and Python skills to build, train, or evaluate deep learning models.

180k – 240k
RemoteAI Research
Datology AI

Research Scientist

Datology AIRedwood City, CA

Research Scientist investigates training data interventions to improve deep learning model quality and behavior. Sources ideas from literature, conducts customer-grounded research, and collaborates with engineers to deliver impact. Requires 3+ years deep learning research and PyTorch proficiency.

180k – 300k
Hybrid3+ YOEAI Research
Machinify

NLP Scientist

MachinifyUnited States

Develops state-of-the-art Visual Question Answering systems for medical records using advanced NLP and Computer Vision techniques. Requires expertise in these fields, strong software engineering skills, and ability to work with noisy data to achieve production-scale model performance.

180k – 230k
RemoteAI Research
Wispr Flow

ML Scientist

Wispr FlowSan Francisco, CA

Develops scalable voice interface features through prototyping, infrastructure building, and R&D. Requires PhD in ML or related field, top conference publications, Python/LLM fluency, and strong engineering skills.

185k – 280k
On-siteAI Research