Founding ML inference Engineer jobs in United States
cer-icon
Apply on Employer Site
company-logo

Cerebro ยท 4 days ago

Founding ML inference Engineer

positionPalo Alto, CA
timeFull-time
remoteOnsite
senioritySenior Level
money$300K/yr - $500K/yr

Cerebro is a stealth-mode, VC-backed AI startup focused on developing cutting-edge machine learning infrastructure. They are seeking a Founding ML Inference Engineer to design high-performance model serving systems and build distributed training infrastructure for next-generation diffusion LLMs.

Staffing & Recruiting
Hiring Manager
Guy Williams
linkedin

Responsibilities

Design and optimize high-performance model serving systems for ultra-low-latency inference of next-generation diffusion LLMs
Build distributed training infrastructure supporting large-scale, state-of-the-art machine learning
Develop observability and monitoring solutions to keep ML systems robust in production environments
Optimize infrastructure costs and resource utilization across powerful GPU clusters
Create efficient data storage and retrieval systems tailored for ML workloads
Collaborate with world-class ML researchers to translate theoretical advances into practical systems

Qualification

ML serving frameworksML frameworksGPU programmingPythonContainerizationCloud platformsDistributed systemsPerformance optimizationMLOps practicesCollaboration

Required

BS/MS/PhD in Computer Science, Engineering, or equivalent experience
Knowledge of ML serving frameworks like vLLM, TensorRT, or ONNX Runtime
Deep understanding of ML frameworks (PyTorch, TensorFlow) from a systems perspective
Familiarity with high-performance computing, GPU programming (CUDA), and distributed training (data/model/pipeline parallelism)
Strong coding skills in Python and at least one systems language (C++, Rust, or Go)
Experience with containerization (Docker), orchestration (Kubernetes), and CI/CD

Preferred

Building and maintaining large-scale ML training clusters
Experience with cloud platforms (AWS, GCP, Azure) and distributed systems
Familiarity with ML workflow orchestration tools (Kubeflow, Airflow)
Skills in performance optimization, profiling, and MLOps practices

Benefits

Health
Dental
Vision
PTO
Flexible vacation

Company

Cerebro

twitter
company-logo
Cerebro partners with companies backed by some of the worlds most prominent VC funds (a16z, Andreessen Horowitz, Sequoia) and accelerator programs including a significant portion of the Y Combinator portfolio to solve startup's most critical hiring challenges across AI, ML & robotics
location
Miami, Florida, US
people-size2-10 employees

Funding

Current Stage
Early Stage
Company data provided by crunchbase