AI Evaluation Research Engineer — Remote

Truelancer AI; United States; Remoto; USD 83.000 - 124.000; Tempo pieno

Vantaggi offerti da questo lavoro

Flexible remote work

Opportunity to work on frontier AI

Descrizione del lavoro

Truelancer AI is seeking a Research Engineer (RE) Curator to design, implement, and review complex AI evaluation tasks for benchmarking advanced AI systems. The role involves executing ML experiments, analyzing results, and producing reproducible research workflows with Python and notebook tools.

Collaborate with researchers in an iterative environment, document findings, and contribute to high-quality technical reports.

Competenze

• MSc/PhD or equivalent research-focused experience with coding, experimentation, and data analysis.
• Experience applying ML/AI methods to research questions with documented results.
• Strong software engineering practices and ability to work in a research environment.
• Familiarity with ML pipelines, experiments, and reproducible workflows.

Mansioni

• Design and implement complex research tasks for evaluating AI systems.
• Develop solutions using Python and modern software tools.
• Plan, run, and analyze ML experiments with statistical interpretation.
• Create reproducible research workflows using notebooks or Colab.
• Document findings and publish technical reports.

Conoscenze

Strong Python programming

Excellent English communication

Research mindset

Independent work

Formazione

MSc in Computer Science

MSc in Artificial Intelligence

MSc in Machine Learning

Equivalent research-focused experience

Strumenti

Git

VS Code

PyCharm

Jupyter Notebook

Google Colab

Descrizione del lavoro

Truelancer AI is seeking a Research Engineer (RE) Curator to design, implement, and review complex AI evaluation tasks for benchmarking advanced AI systems. The role involves executing ML experiments, analyzing results, and producing reproducible research workflows with Python and notebook tools.

Collaborate with researchers in an iterative environment, document findings, and contribute to high-quality technical reports.