Software Engineer

As a Software Engineer you will be the connective tissue of Riven. You will work closely with experts in thermodynamics, machine learning, process modeling, and autonomous experimentation to deploy models, agents, and simulations in software that engineers can rely on., * Manage the backend that trains, manages, and serves our computational models.

• Implement customer facing artifacts and interfaces for interacting with our models and results.
• Build the tool APIs, machine-readable errors, sandboxing, and observability that let agents operate the platform.
• Set engineering standards for a scientific codebase: numerical testing, reproducibility, and versioning that covers models and data as well as source.
• Implement validation at scale: versioned reference data, distributed test suites, and statistical treatment of error.

• 4+ years experience building both backends and user interfaces for scientific or engineering software.
• Experience implementing validation at scale for large bodies of computational output.
• Comfort across the project lifecycle, from early technical prototyping to customer facing deployment.
• Familiarity with architecting agentic frameworks and leveraging agents to solve challenging technical problems.
• Deep scientific and technical curiosity and the ability to quickly absorb a new domain.
• Ability to move quickly and rigorously using agentic engineering approaches.
• Clear interdisciplinary communication and the curiosity to quickly learn and execute in new domains.
• Ability to prioritize, execute, and collaborate with a high degree of agency, a willingness to be wrong, and the ambition to build something that has never existed before.
• Trust, humor, rigor, and an excitement to work in a scrappy, interdisciplinary early-stage environment., * Experience building agentic systems: tool interfaces, evaluation harnesses, or LLM applications in production.
• Deep understanding of numerical optimization - nonlinear solvers, automatic differentiation, or large-scale NLP in practice.
• Background in thermodynamics, chemistry, materials science, or a comparable physical science.
• Scientific visualization, or data-heavy interactive interfaces.
• GPU programming, or performance work on numerical codebases.
• Contributions to open-source scientific software.

$180,000 - $220,000 per year

Compensation decisions are made based on track-record, seniority, and skill set. Additional consideration can be given to candidates with exceptional experience. #J-18808-Ljbffr