Data Engineer

• Design, build and operate the big data platform, including lakehouse, query engines and orchestration, focusing on reliability, performance and cost
• Build and run LLM-serving infrastructure on GPU clusters using vLLM on Kubernetes, including capacity planning, benchmarking and model rollouts
• Operate and evolve the AI gateway with provider routing and failover, virtual keys and quotas, observability and tracing with Langfuse, and team-level usage and cost tracking
• Build fine-tuning and MLOps infrastructure, including training jobs on on-premise and rented GPUs, experiment tracking, an MLflow model registry and a path from experiment to production
• Provide self-service development environments using JupyterHub and Coder for data analysis and model development
• Provide infrastructure for data governance, data quality, access control and privacy, including PII anonymization, across the data and AI lifecycle
• Own monitoring, on-call and incident response for operated services
• Build self-service platforms enabling business data analysts, software engineers and ML engineers to ship independently

Explore AI & Big Data Platform Engineer at Divar. Review requirements and application details.