Source description
About the role
Applied scientist JD
Role Overview: We are hiring Applied Scientists (1 Lead + 2 ICs) to design, build, and optimise GenAI-driven multi-modal pipelines for detecting contextual moments in live video streams. This role focuses on prompt engineering, multimodal inference, and model optimisation using foundation models (Claude, Nova, Bedrock) to maximise detection accuracy.
Key Responsibilities
Design and optimise prompt engineering strategies for foundation models
Build pipelines for multi-modal inference (video + transcript + audio)
Detect and classify custom moments and contextual events Develop reusable frameworks for:
Moment detection templates Structured metadata generation, Fine-tune prompts and configurations to improve:
Accuracy, Precision across moment types
Integrate GenAI outputs into: Structured JSON metadata, Downstream systems and pipelines
Work with AWS services such as: Amazon Bedrock (GenAI models)
Lambda, S3, Kinesis (data pipeline) Collaborate with QA team for output validation and optimisation, Support production rollout and continuous improvement
Required Skills & Experience:
Strong experience in:
Prompt engineering for foundation models (Claude, Nova, etc.).Multi-modal AI systems (vision + NLP).Hands-on experience with:
LLM inference and optimisation
Structured outputs (JSON generation and validation) Strong Python programming and data pipeline skills
Familiarity with AWS cloud stack: Bedrock, Lambda, S3, analytics pipeline
Experience in working with: Video analytics / media AI workflows Real-time or near real-time systems
More at Apptad