Senior AI Platform Engineer

Code Metal, Inc.; Boston (MA); Hybrid; USD 150,000 - 190,000; Full time

Benefits offered by this job

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

Job summary

Code Metal, Inc. is seeking a Platform Engineer to own components from design through production, building services for model serving, agentic infrastructure, observability, and experimentation.

You will debug production issues, review code, mentor teammates, and run benchmarks to steer platform decisions; candidates should have production Python and platform experience with LLMs, PyTorch, and Hugging Face.

Qualifications

• Requires production-grade Python and platform engineering experience.
• Production experience in model serving, agentic infrastructure, or observability/experimentation.
• Familiar with LLMs, inference, experiment design and evaluation, PyTorch, and Hugging Face.
• Experience owning production services, writing design docs, code reviews, and mentoring teammates.

Responsibilities

• Own platform components from design through production operation for model serving, agentic infra, observability, and experimentation.
• Debug production issues, write and review tested code, and collaborate with internal customers and research teams.
• Run benchmarks to inform platform decisions and guide improvements.

Skills

Python

Platform Engineering

Distributed Systems

Kubernetes

CI/CD

LLM Inference

Model Serving

Agentic Systems

Retrieval-Augmented Generation

Observability

Experiment Tracking

PyTorch

Hugging Face

Benchmarking

Model Evaluation

GPU Optimization

Job description

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

Requirements

Requires production-grade Python and platform engineering experience, plus production experience in at least one area: model serving, agentic infrastructure, or observability and experimentation. Candidates should understand LLMs, inference, experiment design, and 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 Systems, Retrieval-Augmented Generation, Observability, Experiment Tracking, PyTorch, Hugging Face, Benchmarking, Model Evaluation, GPU Optimization

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