Diagnose and resolve cross-cutting technical issues affecting system performance and reliability.
Improve platform-wide observability, monitoring, and debugging capabilities.
Investigate AI agent behavior and improve output quality through structured evaluation and iteration.
Refactor and enhance legacy or complex code to improve scalability and maintainability.
Identify architectural bottlenecks and implement system-wide improvements.
Collaborate with product and customer teams to understand real-world failures and translate them into technical solutions.
Improve performance and reliability across infrastructure and services.
Drive higher technical standards and cleaner code practices across the system.
Operate proactively, identifying and solving problems before they are formally scoped.

8+ years of professional software engineering experience.
Strong experience with Python (preferred), particularly in backend or systems environments.
Proven experience working with complex or distributed systems.
Demonstrated ability to diagnose and resolve system-wide performance issues.
Experience working with LLM-based systems or AI agents.
Experience evaluating, tuning, or improving AI model outputs.
Strong understanding of software architecture, scalability, and maintainability principles.
Experience improving code quality across large or evolving codebases.
Solid computer science fundamentals (algorithms, data structures, system design).
Experience working independently with high ownership and minimal oversight.
Strong problem-solving skills and ability to context-switch across infrastructure, backend, and AI-related challenges.
Excellent communication skills and ability to translate ambiguous problems into structured solutions.

Platform AI Software Engineer

Key skills