Qualifications

• 5-7 years of experience in prompt engineering for foundation models, particularly Claude Nova and others.
• Proficient in multimodal AI systems, including vision and natural language processing (NLP).
• Hands-on experience with large language model (LLM) inference and optimization techniques.
• Strong programming skills in Python and expertise in data pipeline development.
• Familiarity with Amazon Web Services (AWS) stack, specifically Bedrock, Lambda, S3, and analytics pipelines.
• Experience in video analytics and media AI workflows, especially in real-time systems.

Responsibilities

• Design and optimize prompt engineering strategies for enhancing foundation model performance.
• Build effective pipelines for multimodal inference integrating video, transcript, and audio data.
• Detect and classify custom moments and contextual events within live video streams.
• Develop reusable frameworks for moment detection templates and structured metadata generation.
• Finetune prompts and configurations to enhance accuracy and precision across various moment types.
• Integrate GenAI outputs into structured JSON metadata for seamless workflow integration.
• Collaborate with QA teams to validate outputs and support ongoing production improvements.

Benefits

• Work in a cutting-edge field focused on generative AI and multimodal processing.
• Opportunity to collaborate with a skilled team of scientists and engineers.
• Access to the latest tools and technologies in AI and cloud computing.
• Potential for continuous learning and skill enhancement in video analytics and AI workflows.