Innodata India is seeking rigorous Technical AI Evaluation Specialists to benchmark LLMs focused on code generation, multi-turn reasoning, and software architecture.
You will evaluate model-generated code for correctness, complexity, and UI fidelity across text-to-code and image-to-code tasks; perform side-by-side analyses using detailed rubrics; and document evidence-based rationales to guide model improvements and RLHF efforts.
#J-18808-LjbffrAI Code & UI Evaluation Engineer in Location not specified at Unknown Company
This position is listed as full time and onsite.