Senior Software Engineer - AI Evaluation / Coding Agents

Turing is looking for Senior Software Engineers to test, benchmark, and improve cutting-edge autonomous coding agents and LLM code-generation models. Key Responsibilities: Author high-difficulty algorithmic challenges, repository-level bug reproductions, and end-to-end unit tests. Evaluate code produced by state-of-the-art coding agents against production standards (security, complexity, scalability). Craft detailed rubrics to grade multi-step agent planning, tool invocation, and automated debugging capabilities. Conduct code reviews across various stacks (Python, TypeScript, Go, Java, Rust) and document subtle logic flaws. Design harness scripts to run and isolate test environments in containerized setups. Requirements: 5+ years of production software engineering experience. Deep expertise in at least two core languages: Python, TypeScript/JavaScript, Go, C++, or Java. Solid grasp of algorithmic complexity (Big O), concurrency patterns, and modular system design. Strong written communication in English to document subtle architectural and security tradeoffs.