Applied Scientist

We are seeking an Applied Scientist to join our team, focused on leveraging existing AI/ML models to detect key moments in sports videos through computer vision and transcript analysis. This role emphasizes prompt engineering, model output validation and integration with inference pipelines rather than custom model development or training.

Responsibilities

Design and optimize prompts for multimodal foundation models such as Claude and Nova to detect custom ad moments in live video frames and audio transcripts

Process test video assets through Amazon Bedrock for custom moments detection using transcript analysis and computer vision

Configure and tune the Bedrock Connector pipeline for each custom moment type

Conduct model comparison studies with accuracy benchmarking on specific content

Validate detection accuracy across multiple sports, genres and live event types and refine prompts to improve accuracy

Build repeatable templates for pipeline processing and structured metadata output

Collaborate with the AWS Elemental Inference team to align on integration requirements

Requirements

5+ years of experience in applied AI/ML with a focus on multimodal models spanning vision and language

Expertise in prompt engineering for large foundation models, with Amazon Bedrock preferred

Familiarity with video/image understanding in live video workflows and near-real-time inference pipelines

Skills in designing evaluation frameworks and benchmarking model accuracy

Experience working in media, advertising or content classification

English proficiency at B2 level or higher

Nice to have

Familiarity with video frames using OpenCV and transcript data for understanding input data

Knowledge of computer vision and natural language processing techniques

Background in sports analytics or media technology

We offer

International projects with top brands

Work with global teams of highly skilled, diverse peers

Healthcare benefits

Employee financial programs

Paid time off and sick leave

Upskilling, reskilling and certification courses

Unlimited access to the LinkedIn Learning library and 22,000+ courses

Global career opportunities

Volunteer and community involvement opportunities

EPAM Employee Groups

Award-winning culture recognized by Glassdoor, Newsweek and LinkedIn