Back
Tier-1 backing plus Bangalore location create moderate applicant competition.
Strong specialization in LLMs, agents, and ML evaluation reduces cross-industry transferability.
Requires concrete LLM/agent shipping experience and ML evaluation expertise, so filters will be strict.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own AI quality standards and improvement processes for Cardboard’s agentic video editor.
Build and maintain trusted evaluation datasets, offline/online evaluations, regression checks, and feedback loops from real product usage data.
Analyze agent performance, identify failure patterns, and collaborate cross-functionally to drive measurable quality improvements.
Experience shipping and operating LLM or agent systems used by real customers.
Strong software engineering skills in TypeScript and/or Python with cross-language proficiency.
Experience building evaluations, datasets, experiments, or AI quality systems.
Work Experience Required: Not explicitly mentioned in the JD. Location: Bengaluru, India.
Senior individual contributor with strong ownership mindset in AI quality and applied ML engineering.
Able to translate vague AI quality issues into measurable evaluation problems and improvements.
Experience or familiarity with multimodal AI, video/media, creative software, human labeling, model grading, fine-tuning, and experiment design/statistics is a plus.