Llm Reliability Jobs

Our work spans efficient LLM training and inference, parallel and diffusion-based generation, sparsity, scaling laws, and training dynamics.

…workflows for performance, efficiency, and reliability.

Preferred Skills Experience with large-scale LLM/inference serving and the systems around it (e.g. vLLM, TensorRT-LLM

Drive reliability in production. Define service-level indicators and objectives for GPU-backed inference.

Drive reliability in production. Define service-level indicators and objectives for GPU-backed inference.

…focus on telemetry, monitoring, and reliability.

…enterprise workloads, so scale and reliability tradeoffs are part of the job.

…focus on telemetry, monitoring, and reliability.

…focus on telemetry, monitoring, and reliability.

Strengthen production reliability. Improve service metrics, tracing, logging, alerts, and diagnostic tools.

…will be the founding quality, reliability, and validation lead for a new GPU Inference

Strengthen reliability and observability.

…— turning integrated features into reliable production releases.

• Build reliable integrations using APIs, MCP, webhooks, event-driven services, SFTP and enterprise integration platforms where appropriate.

The correctness, freshness, and reliability of everything downstream depends on getting this right at scale across a diverse set of upstream sources.