Applied Scientist

Title: Applied Scientist GenAI & Multimodal AI (AWS Bedrock)
Location: Canada (Remote)
Mode: Full-Time (FTE)
End client: AWS (Amazon Web Services)

Role Overview

This role focuses on prompt engineering multimodal inference and model optimization using foundation models such as Claude Nova and Amazon Bedrock to maximize detection accuracy and business value.

Key Responsibilities

• Design and optimize prompt engineering strategies for foundation models.
• Build pipelines for multimodal inference across:
  • Video
  • Audio
  • Transcripts
• Detect and classify custom moments and contextual events.
• Develop reusable frameworks for:
  • Moment detection templates
  • Structured metadata generation
• Fine-tune prompts and model configurations to improve:
  • Accuracy
  • Precision across multiple moment types
• Integrate GenAI outputs into:
  • Structured JSON metadata
  • Downstream systems and data pipelines
• Work with AWS services including:
  • Amazon Bedrock
  • AWS Lambda
  • Amazon S3
  • Amazon Kinesis
• Collaborate with QA teams for output validation and optimization.
• Support production deployment and continuous improvement initiatives.

Required Skills & Experience:

• Strong experience in Prompt Engineering for foundation models (Claude Nova etc.).
• Expertise in Multimodal AI Systems (Computer Vision NLP).
• Hands-on experience with:
  • LLM inference and optimization
  • Structured output generation (JSON)
  • Output validation frameworks
• Strong programming skills in Python.
• Experience building scalable data pipelines.
• Familiarity with AWS cloud services:
  • Amazon Bedrock
  • AWS Lambda
  • Amazon S3
  • Analytics/Data Pipeline services
• Experience in:
  • Video analytics
  • Media AI workflows
  • Real-time or near real-time AI systems