Senior ML Expert: LLM Reasoning & Training Lead (Remote)

Alignerr Corp.; España; Remote; EUR 83,000 - 165,000; Full time

Job summary

Alignerr is seeking a Senior Machine Learning Expert to author reasoning traces that teach LLMs how to plan, reason, and solve problems. This is a remote, flexible hourly contract designed for experienced ML practitioners who understand model decision processes.

You will decompose complex problems into structured steps, design data strategies for multi-step reasoning, and ensure traces align with best practices in model training.

Qualifications

• Experienced in machine learning, AI research, or a closely related technical field — you understand how models reason and where they fail.
• Skilled at decomposing hard problems into clear, documented, logical steps.
• Familiar with LLM evaluation methodologies, training pipelines, or RLHF-style workflows.

Responsibilities

• Author complex, high-fidelity reasoning traces that document how an LLM should plan, use tools, and make decisions across sophisticated technical tasks
• Break down intricate real-world problems into clear, structured, logical steps that models can learn from
• Design and contribute to data strategies that help LLMs navigate multi-step decision-making scenarios reliably
• Review and refine reasoning traces for quality, completeness, and alignment with best practices in model training

Skills

Machine learning

AI research

Problem decomposition

Documentation

RLHF workflows

PyTorch

TensorFlow

Tools

PyTorch

TensorFlow

Kaggle

Job description

Alignerr is seeking a Senior Machine Learning Expert to author reasoning traces that teach LLMs how to plan, reason, and solve problems. This is a remote, flexible hourly contract designed for experienced ML practitioners who understand model decision processes.

You will decompose complex problems into structured steps, design data strategies for multi-step reasoning, and ensure traces align with best practices in model training.