Cosmology & AI Benchmarking Engineer (Remote)

mercor; San Francisco (CA); Híbrido; CAD 96 000 - 138 000; Tempo parcial

Resumo da oferta

Mercor is seeking a STEM Computational Scientific Software & Evaluation Design professional for astrophysics and cosmology tasks. This remote contract role requires 15–20 hours per week and strong Python expertise to design and evaluate research-grade problems using scientific software libraries.

Candidate will work independently with remote compute sandboxes, employing astropy for cosmological calculations and data reduction.

Qualificações

• Graduate-level training in a STEM field (MS/PhD or equivalent).
• Proficiency with scientific software libraries, evidenced by publications or professional work.
• Strong Python programming skills for problem setups and validators.
• Ability to work in Linux/terminal environments with remote compute sandboxes.

Responsabilidades

• Design graduate-level computational problems using domain-specific scientific software libraries.
• Evaluate AI systems' ability to solve research-grade problems and interpret outputs.
• Develop experimental strategies to recover information from data with emphasis on strategic reasoning.
• Calibrate tasks against state-of-the-art AI models and refine problem designs to target difficulty.
• Work independently and asynchronously to iterate on problem designs based on calibration feedback.
• Use astropy and related tools for cosmological calculations and data reduction.

Conhecimentos

Python programming

Scientific software libraries

Research experience

Formação académica

MS/PhD or equivalent research experience

Ferramentas

Astropy

Linux/terminal

Descrição da oferta de emprego

Mercor is seeking a STEM Computational Scientific Software & Evaluation Design professional for astrophysics and cosmology tasks. This remote contract role requires 15–20 hours per week and strong Python expertise to design and evaluate research-grade problems using scientific software libraries.

Candidate will work independently with remote compute sandboxes, employing astropy for cosmological calculations and data reduction.