The opportunity
We challenge the status quo because we know a better supply chain isn’t just possible—it’s essential. Better for our customers.
What you'll do
Design, build, and maintain AI agent workflows that automate carrier: monitoring, performance tracking, exception management, and escalation processes.
Build custom, customer-specific AI agent workflows tailored to individual: carrier, lane, or account requirements, adapting core workflow patterns to unique operational needs.
Write, test, iterate, and optimise prompts for large language models,: ensuring accuracy, reliability, and operational efficiency.
Run structured tests to evaluate prompt performance, comparing variants: against defined criteria and documenting what works, what doesn’t, and why.
Track prompt versions and iterations, maintaining clear records of changes,: evaluation outcomes, and the reasoning behind design decisions.
Identify where LLM outputs fall short of operational requirements and: systematically diagnose and resolve issues through prompt refinement.
What they're looking for
- Work closely with engineers through the handover and deployment process,: ensuring workflows are correctly implemented and behave as intended at go-live.
- Ramp up new use cases post-launch: gradually expanding scope and coverage, surfacing edge cases as real-world volume increases, and refining prompts accordingly.
- Monitor agent performance on an ongoing basis, identifying drift,: degradation, or failure modes and re-iterating on prompts to maintain accuracy and reliability over time.
- Maintain and support existing production workflows throughout their: lifecycle, applying fixes, updates, and enhancements as customer needs, data sources, or underlying models evolve.
