Staff AI Platform Engineer — Lead Production Infra

Code Metal, Inc.; Washington (District of Columbia); Hybrid; USD 205,000 - 250,000; Full time

Benefits offered by this job

Health care plan with 100% premium

401k with 5% matching

Paid Time Off (uncapped vacation)

Flexible hybrid or remote work

Relocation assistance

Job summary

Code Metal, Inc. is seeking a Staff AI Platform Engineer to lead a four-person team and architect the AI enablement stack. You will guide production systems, model gateways, and agent harnesses, collaborating with Applied AI Research to validate platform decisions.

The role emphasizes engineering leadership, platform reliability, and building scalable, verifiable workflows for product teams. Hybrid/remote options are supported.

Qualifications

• Production-grade Python and platform engineering fundamentals: API and service design, distributed systems, containers and Kubernetes, CI/CD, and testing.
• Shipped production agentic systems with reliability considerations.
• Experience with context engineering: retrieval-augmented generation, embeddings, vector or hybrid search, and memory for agents.

Responsibilities

• Set the technical direction and architecture for Code Metal's AI platform and lead the team building it.
• Deploy, benchmark, and tune production inference for open-weight models on vLLM, SGLang, and TensorRT-LLM.
• Own the model gateway that teams use to reach self-hosted and commercial models with robust auth and routing.

Skills

Python

Kubernetes

APIs & services

Distributed systems

OpenTelemetry

PyTorch

Hugging Face

Staff leadership

Design docs

Experiment design

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Code Metal, Inc. is seeking a Staff AI Platform Engineer to lead a four-person team and architect the AI enablement stack. You will guide production systems, model gateways, and agent harnesses, collaborating with Applied AI Research to validate platform decisions.

The role emphasizes engineering leadership, platform reliability, and building scalable, verifiable workflows for product teams. Hybrid/remote options are supported.