About the Position

Join our team as an ML Inference Platform Engineer to build reliable infrastructure for model serving, focusing on latency, throughput, and cost visibility.

Responsibilities

• Design model-serving paths, batching, routing, and rollout mechanisms.
• Profile GPU utilization, memory pressure, tail latency, and failure recovery.
• Build load tests, observability, and repeatable deployment procedures.

Requirements

• Experience operating backend or ML infrastructure under production load.
• Strong Linux and networking fundamentals, with Python, Go, Rust, or C++.
• Ability to compare serving approaches using realistic workloads and cost constraints.

Useful Evidence

• An infrastructure project with measured performance and operational lessons.
• GPU profiling, distributed inference, and custom kernels are useful experience.

Working Terms

• Startup culture, a goal-oriented team, and a research mindset.
• The opportunity to apply your engineering skills to tools and systems for fellow engineers and help shape the future of AI.
• Latest-generation MacBook Pro.
• An in-house GPU cluster for training and experimentation.
• 20 working days of annual leave.
• English courses, educational events, and conferences.
• Medical insurance.

Tools & Systems

NVIDIA Dynamo, vLLM, TensorRT-LLM, Kubernetes, OpenTelemetry.

Relevant experience matters more than knowing every tool listed.

Start a Conversation

Send a CV or profile and one piece of work that helps us understand your contribution.

Apply by email.

Include the role title. Please share only work you have permission to disclose.

How we use application data

More roles in Engineering Lab. Explore the laboratory.

Connect

Engineering Lab

ML Inference Platform Engineer

Build the infrastructure that serves models reliably and makes latency, throughput, and operating cost visible.

Location

Kyiv / remote

Experience

Senior

Working Arrangement

Arrangement to be discussed