About this role

Orcrist is seeking an ML Engineer to productionize NLP/audio/document models for their Intelligence Platform. You will be responsible for packaging, deploying, monitoring, and evaluating models, working with research and product teams to deliver insights globally. This role involves building evaluation pipelines, operating inference systems, and monitoring model quality and performance.

What we are looking for

6

Package and deploy ML models (ASR, translation, OCR, NER, summarization) on Kubernetes
Build and automate model evaluation pipelines
Operate streaming and batch inference systems
Monitor model drift and quality using Prometheus and Grafana
Collaborate with TypeScript teams on data contracts and feedback loops
4-8+ years of ML engineering/MLOps experience

Skills mentioned

3

PythonKubernetesMachine Learning

Work authorization

Must be authorized to work without sponsorship.