22 Nov
|
Jobgether
|
Winnipeg
22 Nov
Jobgether
Winnipeg
Build production inference infrastructure for large language models as a Canada-based Lead/Senior Engineer, optimizing latency, reliability, and costs. This hands-on engineering role develops scalable model-serving platforms for AI-driven professional applications. You will shape technical direction, engineering practices, and operational standards within a newly established team. Collaboration spans model training, evaluation, research, product, and engineering stakeholders. Key Responsibilities:
Build and operate production-grade model-serving infrastructure for large-scale AI workloads Optimize batching, caching, quantization, latency, and operating costs Strengthen observability, monitoring,
and operational visibility Integrate new model releases into serving infrastructure Mentor engineers and contribute to technical strategy Requirements:
Hands-on Kubernetes or comparable infrastructure engineering experience Experience operating model services through scaling and peak traffic Large language model serving or inference optimization experience Solid distributed systems scalability, availability, and reliability background Experience troubleshooting production incidents under real traffic Apply production infrastructure, distributed systems, and inference optimization expertise to advance reliable large language model serving.
📌 Lead LLM Inference Infrastructure Engineer (Winnipeg)
🏢 Jobgether
📍 Winnipeg