- Tel Aviv, Tel Aviv, Israel
- On-site
- Full-time · Mid
- 4+ years
As an ML Ops Engineer, you will own the path from research to production: packaging, release, serving, and keeping models fast, reliable and cost-efficient. You will work closely with our researchers and backend engineers.
Responsibilities
- Build and run the infrastructure that serves ML models in production, on AWS SageMaker and other cloud platforms
- Own the model release flow: packaging, versioning, CI/CD, safe rollout and rollback
- Host and run open-weight models and LLMs on CPU and GPU
- Build pipelines for datasets, training jobs and evaluation, together with Research
- Monitor models in production (latency, errors, quality, drift) and set up alerts
Requirements
- Nice to have: AWS SageMaker
- Nice to have: Azure ML
- Nice to have: Vertex AI
- Nice to have: LLM Serving (vLLM, TGI, Triton)
- Nice to have: Model Optimization (ONNX, quantization)