About Turing:
Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing supports customers in two ways: first, by accelerating frontier research with high-quality data, advanced training pipelines, plus top AI researchers who specialize in coding, reasoning, STEM, multilinguality, multimodality, and agents; and second, by applying that expertise to help enterprises transform AI from proof of concept into proprietary intelligence with systems that perform reliably, deliver measurable impact, and drive lasting results on the P&L
Role Overview:
We are seeking highly specialized Subject Matter Experts (SMEs) in Biology to join an intensive scientific coding project. The primary objective is to create computationally intensive task prompts designed to rigorously evaluate and challenge the capabilities of advanced AI models, specifically Claude Opus 4.5.
This is a high-impact project where experts will craft complex scientific problems that require the AI model to generate Python code capable of producing precise, verifiable numerical results. The goal is to push the boundaries of what AI can accomplish in scientific computing and identify areas where current models fall short.
Responsibilities:
What You Will Do
As a Scientific Computing SME, you will create advanced task prompts that challenge AI models to write scientific Python code. The workflow is as follows:
1. Select a Domain: Choose from Physics, Chemistry, Mathematics, or Biology based on your expertise
2. Select a Subdomain: Narrow down to a specific area within your chosen domain (e.g., Quantum Mechanics, Organic Chemistry, Numerical Analysis, Genomics)
3. Create a Task Prompt: Write a detailed, computationally intensive problem that requires the AI to generate Python code to solve it
4. Define Ground Truth: Specify the expected numerical answer with precision (up to 3 significant digits or 3 decimal places)
5. Ensure Diversity: Create questions across different topics—repetition of similar problems is not allowed
Task Prompt Requirements
Every task prompt you create must meet these criteria:
• Computationally Intensive: Problems should require significant computational effort— numerical simulations, iterative algorithms, complex calculations, or large-scale data processing
• Python Code Output: The AI model must write Python code as the solution, using scientific libraries (NumPy, SciPy, SymPy, etc.)
• Precise Ground Truth: The final answer must be a specific numerical value expressed to 3 significant digits or 3 decimal places (e.g., "The final energy is 2.47 × 10⁻³ J" or "The concentration is 0.0342 M")
• Model-Breaking Difficulty: Questions should be challenging enough to potentially "break" or expose limitations in Claude Opus 4.5
• Self-Contained: All necessary constants, parameters, boundary conditions, and constraints must be provided within the prompt
• Verifiable: The solution must be objectively verifiable against the ground truth answer
Required Qualifications:
Educational Background
• PhD in Biology or a closely related field (Preferred)
• Master's Degree with a minimum of 2 years of research or industry experience in computational/scientific work may be considered
Technical Skills
• Strong proficiency in Python for scientific computing
• Experience with scientific libraries: NumPy, SciPy, SymPy, Pandas, Matplotlib • Understanding of numerical methods, algorithms, and computational complexity • Ability to design problems with precise, verifiable numerical outcomes
Perks of Freelancing With Turing:
Offer Details: