AI Engineer, Product
Is deze vacature iets voor u?
Mijn cv maken Maak uw cv en ontdek uw matchpercentage met deze functie — en met alle andere.
De functie
Join the product team to design and implement an LLM evaluation framework and end-to-end observability for model releases.
Define and track metrics such as task success, helpfulness, hallucination proxies, safety flags, latency and cost.
Run A/B tests for prompts, models, and system prompts, analyze results, and recommend rollout or rollback decisions.
Set up structured logging, tracing, dashboards and alerts to monitor LLM calls and system health.
Lead model release operations with canary and shadow traffic, SLO-based rollbacks and regression detection.
Create reusable templates and documentation for other teams and collaborate with science to diagnose regressions and post-mortems.
Define and track metrics such as task success, helpfulness, hallucination proxies, safety flags, latency and cost.
Run A/B tests for prompts, models, and system prompts, analyze results, and recommend rollout or rollback decisions.
Set up structured logging, tracing, dashboards and alerts to monitor LLM calls and system health.
Lead model release operations with canary and shadow traffic, SLO-based rollbacks and regression detection.
Create reusable templates and documentation for other teams and collaborate with science to diagnose regressions and post-mortems.
Bekijk de volledige vacature
Taken, profiel, vaardigheden en voordelen — maak gratis een account aan.
of
Al een account?
InloggenVergelijkbare vacatures
Andere functies die kunnen passen.