Key Responsibilities :
- Lead and contribute directly to codebase development for GenAI applications.
- Perform code evaluation, including reviewing, testing, and benchmarking generated or human-written code.
- Develop test suites and define code quality metrics such as correctness, efficiency, maintainability, and security.
- Collaborate with AI / ML engineers and product teams to ensure technical feasibility and high performance.
- Contribute to the development, fine-tuning, and evaluation of code generation models and tools.
- Adapt quickly to new programming languages, tools, and GenAI evaluation methodologies.
Required Skills & Experience :
7 to 10+ years of experience building and delivering large-scale, production-grade software systems.Strong programming expertise in at least one of the following languages : Python, Java, C, C++, JavaScriptAbility to write clean, efficient, and secure code and evaluate code in multiple programming languages.Hands-on experience in code review, test automation, and benchmarking software performance.Familiarity with CI / CD pipelines, Git, and unit / integration testing best practices.Preferred Qualifications :
Exposure to Generative AI, Large Language Models (LLMs), or tools like Codex, Copilot, Code Llama, etc.Experience working on code generation, model fine-tuning, or GenAI-powered developer tools.Understanding of AI evaluation techniques such as pass@k, fuzz testing, unit test generation, or synthetic benchmark design.Experience working in a remote, agile, and fast-paced environment(ref : hirist.tech)