Member, Model Training (Post-Training Research)

OpenTrain AI, Inc.

Argentina

Remote

ARS 85,536,000 - 192,456,000

Part time

3 hours ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

OpenTrain AI, Inc. is seeking a Member of Technical Staff for Model Training Research to advance post-training methods for large language and multimodal models. You will probe optimization dynamics, learning objectives, and curriculum strategies while building scalable training pipelines.

The role emphasizes experimental rigor, reproducible research, and collaboration across teams. Applicants from multiple countries are welcome, with at least 20 hours per week commitment for a contractor role.

Qualifications

  • Time commitment: 20+ hours per week.
  • Contractor role at expert level.
  • Hands-on experience training, fine-tuning, or post-training of large language or multimodal models.
  • Strong Python and PyTorch programming, including debugging and optimization of complex training pipelines.
  • Ability to design controlled experiments and reproduce findings with analytical rigor.
  • Background in reinforcement learning, reward modeling, data selection, and curriculum learning is a plus.

Responsibilities

  • Research, implement, and scale post-training methods for large language and multimodal models.
  • Investigate learning objectives, optimization dynamics, exploration strategies, and credit assignment.
  • Develop training recipes using data mixtures, sampling strategies, curricula, and evaluation methods.
  • Design methods that learn from expert demonstrations, human preferences, corrections, and model-generated trajectories.
  • Study how generators, reward models, graders, and training signals work together.
  • Design controlled experiments, ablation studies, and evaluation frameworks for reasoning, generalization, and downstream performance.
  • Lead research initiatives from forming hypotheses and implementing algorithms through large-scale experiments and validation.

Skills

Python
PyTorch
Machine Learning
Deep Learning
Reinforcement Learning
Experimental Design
Research
Optimization
Distributed Training

Tools

PyTorch (core)
CUDA

Job description

Member of Technical Staff, Model Training Research
The work
  • Research, implement, and scale post-training methods for large language and multimodal models.
  • Investigate learning objectives, optimization dynamics, exploration strategies, and credit assignment.
  • Develop training recipes using data mixtures, sampling strategies, curricula, and evaluation methods.
  • Design methods that learn from expert demonstrations, human preferences, corrections, and model-generated trajectories.
  • Study how generators, reward models, graders, and training signals work together.
  • Design controlled experiments, ablation studies, and evaluation frameworks for reasoning, generalization, and downstream performance.
  • Lead research initiatives from forming hypotheses and implementing algorithms through large-scale experiments and validation.
Requirements
  • Time: 20+ hours per week.
  • Level: Expert. This is a contractor role.
  • Required knowledge: Strong foundations in machine learning, deep learning, optimization, and modern model training.
  • Required experience: Hands‑on experience training, fine‑tuning, or post‑training large‑scale language or multimodal models.
  • Required skills: Strong Python and PyTorch programming, including debugging and optimization of complex training pipelines.
  • You must be able to design controlled experiments, interpret empirical findings, formulate hypotheses, and carry out reproducible research with analytical rigor.
  • Useful background includes reinforcement learning, model distillation, reward modeling, data selection, learning dynamics, RLHF, RLAIF, preference optimization, reasoning or agentic reinforcement learning, distributed training, GPU‑based optimization, reward models, verifiers, graders, automated evaluation systems, synthetic data generation, curriculum learning, and iterative self‑improvement.
  • Publications, open‑source work, or production contributions in post‑training or reinforcement learning are also relevant.
  • Skills: Reinforcement Learning & Optimization, Post-Training Algorithms, Training Data Strategy & Curriculum Learning, ML Research & Experimental Design

Open to applicants in

  • Argentina
  • Austria
  • Canada
  • Chile
  • Colombia
  • Egypt
  • France
  • Germany
  • Ghana
  • Greece
  • India
  • Italy
  • Japan
  • Jordan
  • Kyrgyzstan
  • Lebanon
  • Malaysia
  • Mexico
  • Morocco
  • Netherlands
  • Oman
  • Pakistan
  • Philippines
  • Portugal
  • Qatar
  • South Africa
  • Spain
  • Sri Lanka
  • Tunisia
  • United Arab Emirates
  • United Kingdom
  • United States
  • Vietnam
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Post-Training ML Research Scientist (Contract)
Post-Training ML Research Scientist (Contract)

OpenTrain AI, Inc. • Argentina

Remote
ARS 85,536,000 - 192,456,000
Member of Technical Staff, Model Training Infra Platform
Member of Technical Staff, Model Training Infra Platform

OpenTrain AI, Inc. • Argentina

Hybrid
ARS 128,304,000 - 427,680,000
Member of Technical Staff, Model Training (Applied Research)
Member of Technical Staff, Model Training (Applied Research)

OpenTrain AI, Inc. • Argentina

Remote
ARS 205,607,000 - 328,993,000
Remote Model Training Engineer - Applied AI & Robotics
Remote Model Training Engineer - Applied AI & Robotics

OpenTrain AI, Inc. • Argentina

Remote
ARS 205,607,000 - 328,993,000
Enterprise Client Partner, Frontier AI (English)
Enterprise Client Partner, Frontier AI (English)

OpenTrain AI, Inc. • Argentina

Remote
ARS 128,304,000 - 256,608,000
Remote Ai Agentic Training Engineer (Post-Training)
Remote Ai Agentic Training Engineer (Post-Training)

Alignerr Corp. • La Pampa

Remote
ARS 215,229,000 - 292,096,000
Machine Learning Researcher (Systems Engineering)
Machine Learning Researcher (Systems Engineering)

OpenTrain AI, Inc. • Argentina

Remote
ARS 462,643,000 - 822,471,000
Remote Prompt Writer For Ai Training
Remote Prompt Writer For Ai Training

Alignerr Corp. • Ciudad de Mendoza

Remote
ARS 183,391,000 - 275,086,000
Remote Ai Agentic Training Engineer (Post-Training)
Remote Ai Agentic Training Engineer (Post-Training)

1801 Haleon Argentina S.A. • Municipio de Juan José Castelli

Remote
ARS 232,840,000 - 325,976,000
Staff ML Infra Architect: GPU Training & RL Pipelines
Staff ML Infra Architect: GPU Training & RL Pipelines

OpenTrain AI, Inc. • Argentina

Hybrid
ARS 128,304,000 - 427,680,000