Model Serving Engineer

Fundamental · Remote · Europe ·
Fully remoteFull-timeMiddle3–5 years
COMPENSATION
€•• – ••k
0 applicants so far

Listed on the employer's job board (Ashby)

  • Model Serving Engineer
  • Python + Distributed Systems
  • GPU Infrastructure Focus
  • Competitive Salary + Equity
  • Health Coverage Included

Join the Serving team at Fundamental to transform the NEXUS Large Tabular Model into a reliable, high-performance production system. You will bridge research and engineering, tackling unique serving challenges related to structured data and irregular computational behavior.

This technical role focuses on the full inference stack, from Python runtime optimization to GPU serving infrastructure. You will define architecture for distributed execution and ensure efficient operation under real-world workloads for Fortune 100 clients.

What you'll do

  • Optimize Python inference code for concurrency and performance
  • Define architecture for distributed inference and async execution
  • Manage Triton serving layer for model packaging and execution
  • Build observability tools to monitor latency and throughput
  • Collaborate with researchers on model internals and hardware use
  • Solve serving challenges across diverse deployment environments
  • Evaluate new inference runtimes and infrastructure approaches

What you'll need

  • 5+ years in model serving, ML infra, or backend engineering
  • Deep expertise in Python concurrency and GIL behavior
  • Experience building asynchronous and message-driven systems
  • Strong background in high-performance distributed systems
  • Ability to analyze ML model compute and memory characteristics
  • Proficiency in profiling CPU, memory, I/O, and GPU workloads
  • Bachelor's or Master's in Computer Science or equivalent

Nice to have

  • Understanding of GPU architecture and resource utilization
  • Experience with tabular and structured-data ML systems
  • Knowledge of neural networks and deep learning architectures
  • Familiarity with Kubernetes and cloud infrastructure
  • Experience with DevOps tools, containers, and CI/CD

Stack

  • Python
  • Triton
  • Kubernetes
  • Helm
  • GPU

What you get

  • Competitive compensation with salary and equity
  • Comprehensive health coverage for dependents
  • Paid parental leave for all new parents
  • Relocation support for office-based employees