Remote project-based opportunity for software engineers with production experience to author SWE-bench-style coding tasks against real repositories for frontier AI evaluation and training systems.
Full-Stack Software Engineer - Testing & Evaluation
Remote (Global)
$50 – $100/hr
May 12, 2026
Job description
AfterQuery is hiring skilled software engineers with strong full-stack development experience to help build realistic software engineering environments and evaluation tasks for AI systems.
This role focuses on architecting technically substantial projects, structuring reproducible development environments, and creating deterministic testing workflows that mirror real-world engineering practices.
Experience with Docker and containerized workflows is required.
Responsibilities
Develop technically substantial software projects reflecting real-world engineering environments
Create structured software development challenges with:
- Clear documentation
- Reproducible environments
- Deterministic evaluation criteria
Build deterministic test suites to verify:
- Correctness
- Reproducibility
- Stability
Containerize projects using Docker to ensure consistent execution environments
Work across multi-file codebases and realistic engineering architectures
Required Qualifications
Proficiency in at least one modern programming language such as:
- JavaScript / TypeScript
- Java
- Go
- Rust
- C / C++
Experience architecting or maintaining multi-file software projects
Hands-on experience with:
- Docker
- Containerization workflows
- Development environment setup
Strong technical writing and documentation skills
Preferred Qualifications
Experience with:
- Full-stack architectures
- End-to-end application development
Familiarity with:
- Testing frameworks
- Build tools
- Code-quality workflows
- CI/CD tooling
About AfterQuery
AfterQuery is a research lab exploring the boundaries of artificial intelligence through novel datasets and experimentation.
The company is backed by investors including:
- Y Combinator
- Box Group
AfterQuery supports leading AI labs through advanced AI training and evaluation initiatives.
Apply now
You will be redirected to the company's website to complete your application.
Remote project-based opportunity for software engineers with 1–3 years of experience to work on software development, debugging, code review, and technical implementation projects supporting frontier AI systems.
Remote AI training opportunity for college software engineering and computer science experts to create and evaluate coding challenges covering algorithms, debugging, system design, and software engineering best practices.
Review and validate AI-generated coding tasks used to train large language models. Seeking experienced software engineers with strong code review, testing, and technical evaluation skills across multiple programming languages.