Orcrist Technologies

Orcrist Technologies

Orcrist Technologies specializes in providing advanced technology solutions, including data analytics, AI applications, and cybersecurity, aimed at empowering businesses to innovate and transform through the use of artificial intelligence and data-driv...

Internet Software & Services

Description

  • Package and deploy ASR, translation, OCR, NER, and summarization models on Kubernetes using Triton and KServe.
  • Build evaluation pipelines for model quality, latency, and cost, and automate release-gating decisions.
  • Operate streaming and batch inference workflows using Kafka, Temporal, and backfill tooling.
  • Monitor model drift and quality using Prometheus, Grafana, and Evidently.
  • Optimize inference performance and cost across production environments.
  • Collaborate with TypeScript teams on payload schemas, API contracts, and human-in-the-loop feedback loops.
  • Partner with Research and product teams to deliver reliable model enrichment for the platform.

Requirements

  • 4–8+ years of experience in ML engineering or MLOps shipping models to production.
  • Strong Python experience and hands-on experience with PyTorch and Transformers.
  • Experience with Triton, KServe, or similar model serving platforms.
  • Comfortable working with Kubernetes, GitOps, CI/CD, and GPU workload operations.
  • Knowledge of model evaluation metrics, monitoring, and annotation workflows.
  • Eligible to work in Germany.
  • Export-control screening is required for certain programs.
  • Temporal, Beam/Flink, or Ray Serve experience is a plus.
  • ONNX or TensorRT optimization experience is a plus.
  • German language skills at B1+ and familiarity with defense or public safety datasets are a plus.
  • Experience with WhisperX, DeepStream/GStreamer, or vector search integrations is a plus.

Benefits

  • Remote-first work environment in Germany.
  • Regular Berlin meetups.
  • 30 days of vacation.
  • Equipment budget.
  • Learning budget.
  • Modern MLOps stack including Triton, Temporal, Kafka, MLflow/Weights & Biases, Evidently, and Kubernetes.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

AI DevOps Engineer

Zscaler 1K-5K Internet Software & Services

Zscaler is hiring a remote AI DevOps Engineer, with a hybrid preference in San Jose, to build and operate multi-cloud platform automation across AWS, GCP, and Azure while integrating AI-assisted workflows.

Argo CD AWS Azure Bash CI/CD GitOps Kubeflow Kubernetes MLflow MLOps Python Secrets Management Terraform Vertex AI
8 hours, 27 minutes ago

Senior Machine Learning Engineer, Digital Twin Platform

instacart.careers 1K-5K Internet Software & Services

Instacart is seeking a Senior Machine Learning Engineer to build and deploy real-time inventory and shelf-stocking intelligence for its Digital Twin Platform, supporting grocery products used by millions of customers.

AWS Azure Computer Vision GCP Machine Learning Python PyTorch Scikit-learn TensorFlow
9 hours, 26 minutes ago

Applied AI Engineer - India

dscout 51-250 Professional Services

Dscout is hiring an Applied AI Engineer to build, evaluate, and improve reliable LLM-powered agents and product features for enterprise UX research customers.

Machine Learning
9 hours, 27 minutes ago

Product & Technical Co-founder (CPTO) - AI Compliance Platform

FutureSight 11-50 Internet Software & Services

FutureSight is seeking a technical co-founder and CPTO to build and lead an explainable AI RegTech platform that automates compliance review for regulated financial firms and produces audit-ready evidence.

Encryption
9 hours, 41 minutes ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers