EPAM is a leading integral provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential.

We are seeking an
Applied Scientist - AI/ML Engineer
to maximize the potential of large language models through advanced prompt engineering and a deep understanding of video workflows.

In this role, you will heavily iterate on Amazon Bedrock models to optimize outcomes by refining prompts that detect sports moments using transcripts and video frames within a multi-modal framework. You will process test video assets through Amazon Bedrock for custom moments detection,



configure and optimize models to maximize accuracy, and build repeatable templates for pipeline processing and structured metadata output.

Responsibilities
- Design and optimize prompts for multimodal foundation models (Claude, Nova, etc.) to detect custom ad moments in live video frames and audio transcripts
- Conduct model comparison studies with accuracy benchmarking on domain-specific content
- Configure and tune the Bedrock Connector pipeline for each custom moment type
- Validate detection accuracy across multiple sports, genres, and live event types
- Fine-tune prompts iteratively to improve detection accuracy and outcomes
- Collaborate with the AWS Elemental Inference team to align on technical direction
- Develop Python scripts to automate custom moments pipelines when needed
- Build repeatable templates for pipeline processing and structured metadata output

Requirements
- 3+ years of experience in applied AI

📌 Applied Scientist (Colombia)
🏢 EPAM Systems
📍 Colombia