Lead Inference Engineer
Remote regions
GlobalBenefits
5w PTO
Similar Jobs
See allML Systems Engineer, Inference
Runpod
Global
Python
VLLM
CUDA
Inference Engineer
Undisclosed
US
CUDA
Research Engineer - Inference
Prime Intellect
Global
Python
PyTorch
VLLM
Senior ML Engineer | Kimchi (Inference Stack Optimization)
Kimchi
Europe
Python
VLLM
PyTorch
Inference Stack Engineer
Pluralis Research
Global
Distributed Systems
About the Role:
- Work across inference serving, GPU performance, distributed systems, benchmarking, and model optimisation to make serving infrastructure faster and more efficient.
- This is the senior technical seat for AI serving at Aleroy, setting the serving and measurement roadmap while remaining hands-on.
What You Will Own:
- Own and improve the inference serving stack, including prefill/decode disaggregation, continuous batching, KV-cache management, and speculative decoding.
- Drive GPU performance engineering using CUDA, Triton, profiling, and kernel optimisation to eliminate bottlenecks.
- Establish rigorous benchmarking and measurement methodologies, and guide engineers across serving, metrics, and testing.
What We Offer:
- Real ownership of the backend powering the AI inference platform.
- A small, senior team with fast execution and low bureaucracy.
- Competitive salary with performance-based incentives, 24 days annual leave, and health insurance.
Aleroy
Aleroy builds a unified platform for high-performance AI inference, enabling companies to deploy and run AI models at scale through a single API. We work in small, collaborative teams focused on solving complex engineering challenges in scalable AI infrastructure.