Remote Research Engineer - AI Safety & Frontier Models

Singapore AI Safety Hub; Poland; Remote; PLN 448,000 - 673,000; Full time

Benefits offered by this job

Competitive benefits

Leave policies

Job summary

Neo Research (新衡) is seeking Research Engineers to build experimental systems for evaluating frontier models. You will create realistic agent environments, integrate tools, and develop long-horizon evaluation infrastructure, ensuring reliability and reproducibility across complex experiments.

You will collaborate with researchers, shaping evaluation methodology and turning open-ended questions into tractable experiments, with output directly contributing to published safety research.

Qualifications

• Strong Python and general software-engineering skills.
• Experience working with language models, agentic systems, or model evaluations.
• Ability to turn an underspecified research question into a reliable experimental setup.
• Strong engineering practices, particularly around reproducibility, testing, observability, and data integrity.
• Ability to investigate unexpected results across both the model and the surrounding infrastructure.
• Clear technical writing and communication skills.
• Comfort working in an early-stage environment where requirements and research directions evolve.

Responsibilities

• Design, implement, and run evaluations of misalignment and loss-of-control risks in frontier models.
• Build realistic agent environments, scaffolds, and tool integrations for studying behaviour under increasing autonomy.
• Develop infrastructure for long-horizon experiments involving many model calls, actions, tools, and environment states.
• Own experimental reliability and reproducibility across model access, sampling, configuration, environment management, logging, and analysis.
• Work with research scientists to turn open-ended questions into tractable experiments, and identify cases where an apparent model behaviour is actually an artefact of the evaluation.
• Build tools for inspecting and analysing large collections of model trajectories and comparing behaviour across models and experimental conditions.
• Contribute experimental methodology, infrastructure, and technical analysis directly to published research.

Skills

Python

Software engineering

Language models

Experimentation

Observability

Testing

Data integrity

Technical writing

Tools

Docker

Kubernetes

Job description

Neo Research (新衡) is seeking Research Engineers to build experimental systems for evaluating frontier models. You will create realistic agent environments, integrate tools, and develop long-horizon evaluation infrastructure, ensuring reliability and reproducibility across complex experiments.

You will collaborate with researchers, shaping evaluation methodology and turning open-ended questions into tractable experiments, with output directly contributing to published safety research.