Scale ML Inference & Model-Serving Engineer

Mixpeek; San Mateo (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Full benefits (medical, dental, vision

401k

H-1B visa sponsorship and immigration”

Job summary

zaimler is seeking an engineer to own our inference and model-serving infrastructure end to end, enabling production-grade AI agents to run fast and reliably at scale. You’ll report to Sofus and collaborate with ML and infra teams on deployment and scalability.

You will set up and scale inference systems, manage GPU resources for concurrency, and optimize the engine that powers scalable agent orchestration, joining an early engineering team in a cutting-edge context.

Qualifications

• Proven ability to build scalable ML/AI platforms end-to-end for production.
• Deep understanding of the inference stack: vLLM, KV cache, and the optimization layers underneath model serving.
• Experience building distributed AI/ML workloads at scale, connecting them to real product or vertical integrations.
• 3+ years of relevant experience. We care about capability, not tenure.

Responsibilities

• Set up and scale inference/Ray Serve for ML and LLM model serving.
• Scale agent GPU infrastructure for concurrency and efficiency across multiple agent workloads.
• Optimize and improve the engine builder and model server that power scalable agent orchestration.

Skills

Scalable ML platforms

Distributed systems

Model serving

Ray Serve

Tools

Ray Serve

vLLM

KV cache

Distributed systems tooling

Job description

zaimler is seeking an engineer to own our inference and model-serving infrastructure end to end, enabling production-grade AI agents to run fast and reliably at scale. You’ll report to Sofus and collaborate with ML and infra teams on deployment and scalability.

You will set up and scale inference systems, manage GPU resources for concurrency, and optimize the engine that powers scalable agent orchestration, joining an early engineering team in a cutting-edge context.