Senior AI Platform Engineer

Code Metal, Inc.; San Francisco (CA); Híbrido; USD 180.000 - 240.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health Insurance

Dental Insurance

Vision Insurance

401(k) With 5% Matching

Uncapped Paid Time Off

Sick Leave

Public Holidays

Flexible Hybrid or Remote Work

Relocation Assistance

Descripción de la vacante

Code Metal, Inc. in San Francisco seeks a platform engineer to own components from design through production for model serving, agentic infrastructure, and observability.

You will debug production issues, review code, and write design documents while collaborating with internal customers to guide platform decisions. The ideal candidate has production-grade Python, platform engineering fundamentals, and experience with transformers, LLM inference, PyTorch, and Hugging Face.

Formación

• Production-grade Python, platform engineering fundamentals, and production experience in at least one area: model serving, agentic infrastructure, or observability and experimentation.
• Experience owning production services, writing design documents, and mentoring or onboarding teammates.
• Familiarity with transformers, LLM inference, experiment design, benchmarking, and model evaluation; working knowledge of PyTorch and Hugging Face.

Responsabilidades

• Own platform components from design through production operation.
• Debug production issues, write and review tested code and design documents, collaborate with internal customers, and run benchmarks or experiments to inform platform decisions.

Conocimientos

Python

Platform Engineering

Distributed Systems

Kubernetes

CI/CD

LLM Inference

Model Serving

Agentic Infrastructure

Retrieval-Augmented Generation

Observability

Experiment Tracking

PyTorch

Hugging Face

Benchmarking

Model Evaluation

Production Reliability

Herramientas

PyTorch

Hugging Face

Kubernetes

CI/CD tools

Descripción del empleo

Own platform components from design through production operation, building and maintaining services for model serving, agentic infrastructure, observability, or experimentation. Debug production issues, write and review tested code and design documents, collaborate with internal customers, and run benchmarks or experiments to inform platform decisions.

Requirements: Requires production-grade Python, platform engineering fundamentals, and production experience in at least one area: model serving, agentic infrastructure, or observability and experimentation. Candidates should understand transformers, LLM inference, experiment design, benchmarking, and model evaluation; have working familiarity with PyTorch and Hugging Face; and have experience owning production services, writing design documents, reviewing code, and mentoring or onboarding teammates.

Key Skills: Python, Platform Engineering, Distributed Systems, Kubernetes, CI/CD, LLM Inference, Model Serving, Agentic Infrastructure, Retrieval-Augmented Generation, Observability, Experiment Tracking, PyTorch, Hugging Face, Benchmarking, Model Evaluation, Production Reliability

Benefits: Health Insurance, Dental Insurance, Vision Insurance, 401(k) With 5% Matching, Uncapped Paid Time Off, Sick Leave, Public Holidays, Flexible Hybrid or Remote Work, Relocation Assistance