Staff AI Inference Platform Engineer - Remote & Equity

Syllo; EUA; Teletrabalho; USD 190 000 - 230 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Health insurance

Equity

Resumo da oferta

Syllo is scaling its AI platform and seeks a Staff Software Engineer to lead the production inference stack. You will define architecture, evaluate technologies, and build systems that deploy, optimize, and monitor AI models in production.

In this hands-on role you will work with ML, infrastructure, and product teams to establish a robust, scalable foundation for AI model serving, while mentoring engineers and shaping the long-term AI infrastructure strategy.

Qualificações

• Significant experience designing and operating production AI inference systems.
• Experience building or leading production LLM serving infrastructure.
• Proficiency with modern inference runtimes and frameworks (e.g., vLLM, TensorRT-LLM, Triton).
• Strong background in distributed systems or high-performance platform engineering.
• Experience optimizing inference performance (latency, throughput, memory, cost).
• Experience operating GPU infrastructure in production.
• Proficiency in Python and at least one systems language (Go, Rust, or C++).
• Proven ability to lead technical architecture for complex infra initiatives.

Responsabilidades

• Lead the design and development of the production inference platform.
• Define the roadmap for inference infrastructure, model serving, and runtime optimization.
• Build and operate scalable, cost-effective systems for serving large language models in production.
• Evaluate and integrate modern inference technologies and runtimes.
• Optimize latency, throughput, GPU utilization, memory efficiency, and costs.
• Develop systems for model deployment, traffic routing, autoscaling, scheduling, and observability.
• Partner with ML engineers to productionize new models and techniques.
• Establish benchmarking methodologies to evaluate models and hardware.
• Decide when to build internally vs. adopt open-source or commercial solutions.
• Mentor engineers and define AI infra best practices.

Conhecimentos

LLM serving

Distributed systems

Python

Systems programming

Model deployment

Performance optimization

Production AI infra

Ferramentas

vLLM

SGLang

TensorRT-LLM

Triton Inference Server

Hugging Face TGI

NVIDIA Dynamo

Descrição da oferta de emprego

Syllo is scaling its AI platform and seeks a Staff Software Engineer to lead the production inference stack. You will define architecture, evaluate technologies, and build systems that deploy, optimize, and monitor AI models in production.

In this hands-on role you will work with ML, infrastructure, and product teams to establish a robust, scalable foundation for AI model serving, while mentoring engineers and shaping the long-term AI infrastructure strategy.