Senior Software Engineer – LLM Evaluation (US-based)

What You'll Do7

• Curate and correct code examples in Python, C/C++, Rust, Go, Java, and JavaScript (including ReactJS) for AI model training.
• Evaluate AI-generated code for systems-level correctness, performance, and reliability.
• Build agents that verify the quality of infrastructure and systems-level code and spot error patterns.
• Work with cross-functional teams to improve AI-driven coding solutions against industry benchmarks.
• Formulate hypotheses about steps in the software engineering cycle (prototyping, architecture design, API design, production implementation, launch, experiments, monitoring, operational maintenance) and assess model capabilities on them.
• Design verification mechanisms that automatically check solutions to software engineering tasks.
• Provide clear, structured evaluation rationales in written and oral communication.

Requirements5

• 3+ years of software engineering experience.
• Strong expertise in systems programming, infrastructure, or backend development using Python, C/C++, Rust, and Go.
• Experience building and deploying scalable, production-grade software with modern languages and tools.
• Deep understanding of software architecture, design, development, debugging, and code quality/review assessment.
• Excellent oral and written communication skills for clear, structured evaluation rationales.

Preferred Qualifications2

• Experience at high-scale engineering organizations like Google, Microsoft, Apple, Amazon, or Meta.
• Graduation from programs with strong CS foundations such as University of Washington, University of Illinois Urbana-Champaign, UT Austin, University of Michigan, Purdue, or comparable institutions.

Who Should Apply

Candidates with 3+ years of software engineering experience and strong systems programming skills in Python, C/C++, Rust, and Go will thrive here. The role suits engineers who have built production systems at scale and can clearly explain code quality assessments. If you enjoy evaluating AI-generated code and designing verification mechanisms, apply.