Ask HN: What's the best hands-on path to learn ML inference infrastructure?

I'm a backend engineer with 8+ years of experience. Most of my work has been APIs, distributed systems, streaming/real-time systems and cloud-infra.

I'm trying to move towards ML inference infrastructure: model serving, batching, etc. but based on my experience, it has been difficult to get a callback for such jobs.

For people working in this area: what projects or experience would actually convince you that a backend engineer is ready to work on inference infra?