Senior AI Software Performance Engineer

Location: Remote

Position Type: Full-time

About the Role

We are seeking a talented and driven AI Software Performance Engineer to join our advanced

technology group. In this role, you will act as a key technical expert, working directly with

internal engineering teams, strategic partners, and high-profile clients to accelerate, optimize,

and deploy cutting-edge AI solutions.

Your mission will be to bridge the gap between complex AI workloads and underlying hardware

capabilities, ensuring maximum efficiency and top-tier performance.

Key Responsibilities

Performance Optimization: Analyze, profile, and characterize client AI workloads to

deliver fully optimized configurations for targeted hardware infrastructure.

Model Engineering: Research industry trends to prototype new solutions. Modify

existing AI models, adjust parameters, and apply quantization techniques to resolve

bottlenecks and enhance runtime performance.

Ecosystem Collaboration: Partner with framework engineers and product development

teams to align future hardware designs with emerging AI software requirements.

Technical Advising: Serve as a trusted consultant for strategic enterprise customers,

guiding them through complex deployment challenges.

Benchmarking: Develop competitive benchmarking collateral and translate real-world

workload data into actionable requirements for future product generations.

Requirements

Core Qualifications:

2+ years of hands-on experience in software profiling and performance tuning using

Python (proven track record of identifying and resolving code-level bottlenecks).

1+ year of experience working with Transformers and Large Language Models

(LLMs) within the PyTorch ecosystem, including a solid understanding of LLM

architecture.

1+ year of practical experience with container orchestration platforms like Kubernetes

or Red Hat OpenShift.

Strong analytical thinking, problem-solving skills, and a proactive attitude toward

technology.

Excellent technical and non-technical communication skills in English, with the ability to

influence stakeholders.

Nice to have:

Experience with Cloud Service Providers (AWS, GCP, or Azure).

Familiarity with modern LLM serving frameworks (e.g., vLLM, Sglang).

Deep understanding of hardware memory utilization, virtualization, and Linux containers.

Previous experience in direct customer-facing technical roles.

Education & Experience

Bachelor's degree in Computer Science, Computer/Electrical Engineering, Math,

Physics, or a related field + 5 years of industry experience, OR

Master's degree in the fields above + 3 years of industry experience, OR

PhD in the fields above + 1 year of industry experience.