Remote Chemistry Domain Expert for AI Benchmarking

Synthires; United States; Remote; USD 124.000 - 193.000; Vollzeit

Zusammenfassung

Synthires is seeking a Chemistry Domain Expert for remote engagement in the United States to advance AI benchmarking in real-world chemistry tasks. You will evaluate chemistry tasks, develop reference solutions, and design research-level benchmarks that measure model performance.

The role emphasizes collaboration with researchers to establish evaluation criteria and to improve AI reasoning and scientific reliability.

Qualifikationen

• PhD in Chemistry, Chemical Engineering, or related field.
• Senior research experience as faculty, PI, staff/senior scientist, or equivalent.
• Specialization in at least one chemistry domain (organic, synthetic, physical, computational, inorganic, materials, analytical chemistry, or chemical biology).
• Hands-on experience using large language models in professional or research work.
• Excellent scientific judgment and written communication skills.
• Based in the United States.

Aufgaben

• Evaluate chemistry tasks and AI-generated outputs for scientific accuracy and feasibility.
• Identify errors in reaction mechanisms, stoichiometry, thermodynamics, and spectral interpretation.
• Develop precise problem specifications and rigorous reference solutions.
• Design challenging, research-level chemistry problems and evaluation benchmarks.
• Collaborate with researchers and experts to establish clear evaluation criteria.
• Provide structured feedback to improve AI reasoning and scientific reliability.

Kenntnisse

LLM experience

Scientific writing

Collaboration

Ausbildung

PhD in Chemistry or related field

Jobbeschreibung

Synthires is seeking a Chemistry Domain Expert for remote engagement in the United States to advance AI benchmarking in real-world chemistry tasks. You will evaluate chemistry tasks, develop reference solutions, and design research-level benchmarks that measure model performance.

The role emphasizes collaboration with researchers to establish evaluation criteria and to improve AI reasoning and scientific reliability.