AIWorkJobs
Micro1 logomicro1Platform listing

Member of Technical Staff, Model Training (post-training research)

Explore how algorithms, training data, and evaluation shape reasoning, generalization, and agent capabilities in large language and multimodal models. You’ll test post-training approaches such as reinforcement…

Remote · Eligibility not specifiedFull-time
Work arrangement
Remote
Eligibility
Eligibility not specified
Engagement
Full-time
Compensation
$7–$8/hr
Specialty
Machine Learning & AI

About the role

Explore how algorithms, training data, and evaluation shape reasoning, generalization, and agent capabilities in large language and multimodal models. You’ll test post-training approaches such as reinforcement learning, distillation, and data-efficient training, then turn research findings into scalable methods. The role spans experimental machine learning research and large-scale model development, from forming hypotheses to validating results.

What you would do

  • Research, implement, and scale post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and on-policy distillation (OPD) for language and multimodal models.
  • Study learning objectives, optimization behavior, exploration, and credit assignment to improve training stability, sample efficiency, and capability development.
  • Build training recipes that coordinate data mixtures, sampling, curricula, and evaluation methods.
  • Develop ways for models to learn from expert demonstrations, human preferences and corrections, and model-generated trajectories; identify where human feedback helps most.
  • Study how generators, reward models, and graders develop together, and improve model performance and the training signals that guide it.
  • Create controlled experiments, ablation studies, and evaluation frameworks to measure generalization, reasoning, and results on realistic downstream tasks.
  • Lead research initiatives from selecting promising questions and implementing algorithms through large-scale experiments and result validation.

Requirements

  • Strong grounding in machine learning, deep learning, optimization, and current model-training methods.
  • Practical experience training, fine-tuning, or post-training large language or multimodal models.
  • Technical expertise in at least one area such as reinforcement learning, model distillation, reward modeling, data selection, or learning dynamics.
  • Proficiency in Python and PyTorch, including implementation, debugging, and optimization of complex training pipelines.
  • Experience designing controlled experiments, interpreting model behavior, and turning empirical findings into research directions.
  • Ability to work through ambiguous research questions, form hypotheses, and revise approaches based on experimental evidence.
  • Strong analytical and research skills, with attention to reproducibility, scientific rigor, and measurable results.

Preferred qualifications

The source marks these as preferred, not required.

  • Experience with RLHF, RLAIF, preference optimization, or reinforcement learning for reasoning and agent tasks.
  • Familiarity with distributed training, large-scale experiments, and GPU-based model optimization.
  • Experience building reward models, verifiers, graders, or automated evaluation systems.
  • Contributions to post-training, reinforcement learning, or related research through publications, open-source work, or production systems.
  • Experience with synthetic data generation, curriculum learning, or iterative self-improvement.

Who should apply

Candidates with hands-on experience training large language or multimodal models and technical depth in areas such as reinforcement learning, distillation, or reward modeling should consider this role. Strong Python and PyTorch skills, experimental judgment, and a research focus on measurable, reproducible results are key.

How applying works on Micro1

Apply through the opportunities portal, complete an AI interview, verify your identity, and join the certified talent pool.

  1. Apply through the opportunities portal or accept a platform invitation.
  2. Complete the AI interview covering communication, reasoning, and role skills.
  3. Verify your government ID and sign the platform contract.
  4. Join the certified talent pool and wait for project matching.

Typical timeline: Micro1 does not publish a fixed interview length. Certification is typically reviewed within 30 days.

Paid steps: Not stated by the source

Certification does not guarantee a project placement.

Process checked Nov 19, 2026. AIWorkJobs does not submit applications or charge a fee. Read the full Micro1 process and its official source on the Micro1 page.

Skills mentioned by the source

  • Reinforcement Learning & Optimization
  • Post-Training Algorithms
  • Training Data Strategy & Curriculum Learning
  • ML Research & Experimental Design

Specialty areas

Specialties come from the source platform’s category taxonomy and are used to filter the job index.

Listing reference: member-of-technical-staff-model-training-post-training-research-0a40f3. Source: Micro1. If something here contradicts the source, the source controls. Report a correction.

Related roles

Other work on the index.

See more in this category

micro1

Member of Technical Staff, Model Training (applied research)

You will develop application-specific models across language, multimodal AI, robotics, and autonomous agents. The work spans the full development cycle: translating use cases into training data and objectives, adapting and evaluating models, then preparing them for deployment. You will connect applied machine learning research with production engineering, with an emphasis on task quality, inference speed, and computational cost.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Full-time
Compensation
$7–$8/hr
  • Model Training & Adaptation
  • Multimodal AI
  • Robotics & Agent Learning
Machine Learning & AIView job

Mercor

LLM Research Scientist (Pre-training & Computer Vision & Adversarial Robustness)

Tackle open-ended empirical research across language and vision, from training image models from scratch to fine-tuning open-weight LLMs. The work calls for hands-on research experience and practical judgment under tight data, compute, model-size, and latency budgets. You should bring depth in at least one of the listed research areas, such as adversarial robustness, generative modeling, multilingual pre-training, or LLM post-training.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Hourly
Compensation
$100–$120/hr
  • machine learning
  • deep learning
  • pytorch
Machine Learning & AIView job

Ethos

Training / Onboarding / L&D Specialist

Apply your learning and development experience to help train a foundational AI lab’s language model on professional documents, spreadsheets, and slide decks. You’ll create, assess, and refine materials for onboarding, facilitator training, curriculum planning, engagement tracking, manager enablement, and skills assessment.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Part-time
Compensation
$70/hr
  • learning and development
  • corporate training
  • onboarding
Machine Learning & AIView job

AfterQuery

Machine Learning Research Expert

AfterQuery creates evaluation data that AI labs use to assess and improve their models. You’ll draw on your own research to develop and solve machine learning analysis problems covering experiment design, ablations, model evaluation, and behavior. The role suits hands-on researchers rather than engineers focused on deployment, data engineers, or annotators. Work remotely with an asynchronous schedule and no fixed hours.

Location and eligibility
Remote · Eligibility not specified
Engagement type
Not specified
Compensation
$115/hr
  • machine learning
  • machine learning research
  • python
Machine Learning & AIView job