Remote QA leadership opportunity for experienced chemistry professionals to oversee AI training quality, review scientific reasoning and reaction-based content, evaluate calculations and laboratory-related outputs, ensure safety awareness, and support contributors across chemistry AI projects.
LLM Expert - Chemistry
Job description
Job Summary
Turing is seeking a Chemistry LLM Expert to support the development, evaluation, and improvement of advanced AI systems for chemistry, chemical engineering, materials science, and related scientific domains.
This role combines deep scientific expertise with AI evaluation, dataset development, benchmarking, and programming. You will help improve the accuracy, reasoning capabilities, and practical usefulness of large language models (LLMs) used in scientific and engineering applications.
Key Responsibilities
- Develop chemistry-focused datasets, benchmarks, problem sets, and evaluation tasks for AI model assessment
- Create reference solutions, grading rubrics, and automated assessment frameworks
- Evaluate AI-generated responses for scientific accuracy, chemical reasoning, engineering correctness, and computational accuracy
- Build Python-based evaluation pipelines, automation workflows, data processing tools, and API integrations
- Identify model weaknesses and failure patterns
- Recommend improvements to increase accuracy, reliability, and scientific reasoning quality
- Collaborate with AI researchers, machine learning engineers, and evaluation teams
Required Qualifications
- Master's degree or Ph.D. in Chemistry, Chemical Engineering, Materials Science, or related scientific disciplines
- Strong expertise in chemistry, chemical engineering, materials science, and scientific problem-solving
- Proficiency in Python, scientific computing, and data analysis tools
- Familiarity with Large Language Models (LLMs), prompt engineering, AI evaluation, and generative AI systems
- Strong analytical and critical-thinking abilities
- Excellent written communication, technical documentation, and scientific writing skills
About Turing
Turing partners with leading AI laboratories and global enterprises to advance frontier AI systems. The company supports AI development through high-quality training data, evaluation frameworks, reinforcement learning environments, and domain-specific expertise.
Engagement Details
- Contractor engagement
- Fully remote
- Contract duration: 24 weeks
- Full-time, 40 hours per week
- Minimum 4 hours overlap with Pacific Time (PST)
Impact
This role directly contributes to improving scientific reasoning, technical accuracy, and domain expertise within next-generation AI systems used across chemistry and engineering applications.
You will be redirected to the company's website to complete your application.