.txt builds structured generation: we make language models produce output that follows a given format, by deciding at every decoding step which tokens are allowed. We compile a JSON Schema, a regex, a grammar, a list of function definitions or a policy into that decision, fast enough to run inside the decoding loop. This is how .txt builds reliable and safe agents. We're looking for a developer to work on the parsers and compilers at the center of it.
The Role.txt builds structured generation: we make language models produce output that follows a given format, by deciding at every decoding step which tokens are allowed. We compile a JSON Schema, a regex, a grammar, a list of function definitions or a policy into that decision, fast enough to run inside the decoding loop. This is how .txt builds reliable and safe agents. We're looking for a Rust developer to own the part of it that has to be fast: the automata, indexes and parsers that run at every decoding step. You'd turn what the rest of the team writes into production-ready Rust, with the Python bindings and C++/CUDA glue to put it inside an inference engine, and the benchmarks to prove it stays fast.
What You Will DoProject Leadership: Initiate and drive the development of mission-critical Rust projects from conception through deployment.
Performance Engineering: Write and optimize parsing code with a strong emphasis on performance, supported by automated benchmarking.
Data Structures & Algorithms: Ability to design, implement, and readily debug formal grammars, efficient parsers, standard and non-standard automata, and general text-based indexing/search.
Cross-Functional Collaboration: Work with other teams to integration their work into production-ready Rust.
Tooling & CI/CD: Utilize advanced profiling, debugging, and continuous integration tools to maintain and enhance code quality in non-trivial and consistent ways.
Proven Rust Experience: Demonstrated ability to lead and contribute to sophisticated, collaborative Rust projects.
Professional Development Skills: A track record of developing well-tested, high-performance software.
Tooling Expertise: Expertise with code profiling and debugging. Experience with automated workflows in CI.
Multi-language Proficiency: Ability to learn and/or work with the following technologies: CUDA, C/C++, Rust/Python bindings.
A Collaborative Mindset: Excellent communication skills and a proactive approach, ideally suited for an early-stage startup culture.
🧭 The problem matters
Every agent that takes real actions needs a layer that guarantees it can only do what it was asked. The parser and compiler work in this role is what enables this guarantee.
🌐 Remote first
Work from anywhere in the world. We communicate mostly in writing and favor occasional organic discussions over recurring large team meetings.
💸 Competitive compensation and benefits
Market-rate salary plus stock options, health and dental insurance, and a 401(k) for US employees. We'll also get you a GPU if you don't have one.
.txt is a fully remote company with the majority of the team in the US and EU.
To facilitate real-time collaboration, we require team members to be available, on a daily basis, for at least 3 hours of overlap with morning New York City (Eastern Time Zone) business hours, 8am - 1pm.
ApplyingPlease provide a 1-page resume in English.
Only apply to one position at a time.
Similar Jobs
What you need to know about the Colorado Tech Scene
Key Facts About Colorado Tech
- Number of Tech Workers: 260,000; 8.5% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Lockheed Martin, Century Link, Comcast, BAE Systems, Level 3
- Key Industries: Software, artificial intelligence, aerospace, e-commerce, fintech, healthtech
- Funding Landscape: $4.9 billion in VC funding in 2024 (Pitchbook)
- Notable Investors: Access Venture Partners, Ridgeline Ventures, Techstars, Blackhorn Ventures
- Research Centers and Universities: Colorado School of Mines, University of Colorado Boulder, University of Denver, Colorado State University, Mesa Laboratory, Space Science Institute, National Center for Atmospheric Research, National Renewable Energy Laboratory, Gottlieb Institute



