About SandboxAQ
SandboxAQ is a high-growth company delivering AI solutions that address some of the world's greatest challenges. The company’s Large Quantitative Models (LQMs) power advances in life sciences, financial services, navigation, cybersecurity, and other sectors.
We are a global team that is tech-focused and includes experts in AI, chemistry, cybersecurity, physics, mathematics, medicine, engineering, and other specialties. The company emerged from Alphabet Inc. as an independent, growth capital-backed company in 2022, funded by leading investors and supported by a braintrust of industry leaders.
At SandboxAQ, we’ve cultivated an environment that encourages creativity, collaboration, and impact. By investing deeply in our people, we’re building a thriving, global workforce poised to tackle the world's epic challenges. Join us to advance your career in pursuit of an inspiring mission, in a community of like-minded people who value entrepreneurialism, ownership, and transformative impact.
About the Role
SandboxAQ is seeking a hands-on computational scientist or engineer to lead the CFD Algorithm Development Project. This role involves developing and deploying a differentiable Computational Fluid Dynamics (CFD) framework on multi-GPU and multi-node systems to optimize chemical reactor designs.
The ideal candidate will combine strong technical depth in CFD, GPU programming, and differentiable simulation with practical experience in model validation and high-performance computing (HPC). You will be responsible for delivering several critical milestones that advance our mission of building AI-driven, physics-based optimization tools for next-generation catalytic reactors.
What You’ll Do:
Lead development of differentiable CFD solvers for non-isothermal and reactive flow simulations on mulit-node multi-GPU hardware using JAX
Design, implement, and containerize code to ensure reproducibility, scalability, and ease of deployment across HPC GPU environments.
Develop optimized parallel linear solvers using FFT or other matrix decompositions
Extend existing implementation of immersed boundary method to complex geometries and non-periodic boundary conditions
Extend and validate CFD capabilities from single-node to multi-node GPU systems for both non-reactive and reactive flow regimes.
Integrate transport equations for up to 50 chemical species using linear numerical methods.
Validate simulation accuracy against benchmark results and fixed-bed reactor configurations.
Develop gradient-based optimization scripts to iteratively modify reactor designs based on objective functions defined by catalyst activity and selectivity.
Collaborate closely with AI model developers to link catalyst property predictions with reactor-scale flow optimization.
Generate comprehensive technical reports summarizing algorithms, scalability, differentiability, and validation results for milestone reviews.
Required Qualifications
PhD or MS in Computation Physics, Mechanical or Chemical Engineering, Computer Science or equivalent discipline.
3+ years (including PhD) of hands-on experience in CFD code development, preferably on GPUs
Proven expertise building scalable scientific software on multi-GPU systems using JAX, PyTorch, CUDA, MPI frameworks or similar.
Full fluency across all of: numerical linear algebra, numerical methods for solving PDEs, sparse and dense linear solvers, immersed boundary methods
Excellent Python programming skills, with experience in JAX a prerequisite
Ability to work independently, manage multiple deliverables, and produce clear technical documentation.
Preferred Qualifications
PhD + 3 years industry experience in Computational Physics, Mechanical/Chemical Engineering, Computer Science or related field
Proven expertise in CFD code development for non-isothermal flow, transport equations, and reactive flow modeling.
Proven expertise with differentiable computational fluid dynamics, and/or gradient-based optimization of complex CFD objectives (i.e. adjoint optimization, auto-diff a.s.o)
Proven experience across the full stack of scientific software development including PR submission, code review, unit-testing, integration testing, containerization with Docker and enroot,, and deployment on GPU-HPC systems using k8s, Google Cloud Batch, slurm or similar.
Proven expertise in chemical reactor and multi-physics modeling (e.g., reactive flow, energy and mass transport in fixed-bed or catalytic systems).
Demonstrated track record of delivering project milestones and publishing high-quality technical results.
The US base salary range for this full-time position is expected to be $154k - $216k per year. Our salary ranges are determined by role and level. Within the range, individual pay is determined by factors including job-related skills, experience, and relevant education or training. This role may be eligible for annual discretionary bonuses and equity.
SandboxAQ Welcomes All
We are committed to fostering a culture of belonging and respect, where diverse perspectives are actively sought and valued. Our multidisciplinary environment provides ample opportunity for continuous growth - working alongside humble, empowered, and ambitious colleagues ready to tackle epic challenges.
Equal Employment Opportunity: All qualified applicants will receive consideration regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status.
Accommodations: We provide reasonable accommodations for individuals with disabilities in job application procedures for open roles. If you need such an accommodation, please let a member of our Recruiting team know.
Read: Guidance for candidates on using AI Tools in interviews
