Found Description
Responsibilities
- Package and deploy models (ASR, translation, OCR, NER, summarization) using Triton/KServe on Kubernetes
- Build evaluation pipelines (WER, BLEU, F1, latency, cost) and automate release gating
- Operate streaming and batch inference via Kafka, Temporal, and backfill tooling
- Monitor drift and quality with Prometheus, Grafana, and Evidently
- Optimize inference cost and performance
- Collaborate with TypeScript teams on payload schemas, contracts, and human-in-the-loop feedback loops
Requirements
- 4–8+ years of ML engineering or MLOps experience shipping models to production
- Strong Python and PyTorch/Transformers skills
- Experience with Triton/KServe or similar
- Proficiency with Kubernetes, GitOps, CI/CD, and GPU workload operations
- Knowledge of evaluation metrics, monitoring, and annotation workflows
- Eligibility to work in Germany