Qualifications

• 5-7 years of experience in prompt engineering for foundation models like Claude and Nova.
• Demonstrated expertise in multimodal AI systems, covering vision and natural language processing (NLP).
• Hands-on experience with large language model (LLM) inference and optimization.
• Solid programming skills in Python with experience in data pipeline development.
• Familiarity with AWS services including Bedrock, Lambda, and S3, specifically in analytics pipelines.
• Proficient in generating and validating structured outputs in JSON format.
• Experience with video analytics and media AI workflows, particularly in real-time systems.

Responsibilities

• Design and optimize prompt engineering strategies for foundation models.
• Build pipelines for multimodal inference involving video transcript and audio.
• Detect and classify custom moments and contextual events in live streams.
• Develop reusable frameworks for moment detection templates and structured metadata generation.
• Finetune prompts and configurations to enhance accuracy and precision across moment types.
• Integrate Generative AI outputs into structured JSON metadata for downstream systems.
• Collaborate with the QA team to validate and optimize output quality.

Benefits

• Flexible work arrangements to support work-life balance.
• Opportunities for continuous learning and professional development.
• Access to cutting-edge technologies and tools in AI and machine learning.
• Collaborative team environment fostering innovation and creativity.