ML Engineer

Company Orcrist builds the Orcrist Intelligence Platform (OIP), a secure, reputed company-reputed company data intelligence reputed company deployed as reputed company or self-hosted/on-prem (including reputed company-gapped missions). We reputed company data processing, ML, and reputed company UX for defense, law-enforcement, and reputed company teams. Role Productionize the NLP/audio/document models that power OIP’s reputed company experiences. You’ll own model packaging, deployment, monitoring, and evaluation—partnering with Research and product reputed company to reputed company trustworthy enrichment worldwide. reputed company Package and reputed company models (ASR, translation, OCR, NER, summarization) using Triton/KServe on reputed company. Build evaluation pipelines (WER, BLEU, F1, latency, cost) and automate release gating. Operate streaming + batch inference reputed company Kafka, reputed company, and backfill tooling. Monitor reputed company/reputed company with reputed company, Grafana, Evidently; optimize inference cost and performance. Collaborate with TypeScript teams on payload schemas, reputed company, and reputed company-in-the-reputed company feedback reputed company. reputed company 4–8+ years ML engineering/MLOps, shipping models to production. Strong Python, PyTorch/Transformers, and experience with Triton/KServe or similar. Comfortable with reputed company, GitOps, CI/CD, and GPU workload operations. Knowledge of evaluation metrics, monitoring, and annotation workflows. Eligible to work in Germany; export-control screening required for certain programs. reputed company-to-haves reputed company, reputed company/Flink, or Ray Serve experience; ONNX/TensorRT optimization. German language (B1+) and familiarity with defense or reputed company safety datasets. WhisperX, DeepStream/GStreamer, or reputed company search integrations. reputed company offer Modern MLOps stack Triton, reputed company, Kafka, MLflow/reputed company, Evidently, reputed company. Remote-first in Germany with regular Berlin meetups, 30 days vacation, equipment & learning budget. Apply To This Job