AI Platform Engineer

Infralyne; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Remote-friendly

Overlap with Asia/Europe working hours

Job summary

Infralyne is hiring a Platform Engineer to build the foundations behind production AI products, including model access, retrieval, evaluation, and operational visibility. You will work across product and engineering to make uncertain model behavior measurable and operable for client teams.

You will develop model gateways, retrieval services, and evaluation pipelines, defining metrics for quality, latency, cost, and human intervention. Strong collaboration and technical writing are essential.

Qualifications

• Strong backend or platform engineering fundamentals.
• Experience operating data-intensive services or systems backed by machine learning models.
• Clear technical writing and ability to collaborate calmly across disciplines.
• Sound judgment about when to standardize and when a simpler approach is appropriate.

Responsibilities

• Build model gateways, retrieval services, evaluation pipelines, and operational tools.
• Turn ambiguous AI behavior into clear engineering expectations in collaboration with product teams.
• Define useful measures for quality, latency, cost, and the need for human intervention.
• Document systems so client teams can operate and extend them.
• Contribute to platform decisions across product and engineering boundaries.

Skills

Backend engineering

Platform engineering

Data-intensive services

Technical writing

Cross-disciplinary collaboration

Judgment about standardization

Job description

Role overview

Build the platform foundations behind production AI products, spanning model access, retrieval, evaluation, and operational visibility. You will work across product and engineering to make uncertain model behavior measurable, operable, and easier for client teams to extend.

Responsibilities

• Build model gateways, retrieval services, evaluation pipelines, and operational tools.
• Turn ambiguous AI behavior into clear engineering expectations in collaboration with product teams.
• Define useful measures for quality, latency, cost, and the need for human intervention.
• Document systems so client teams can operate and extend them.
• Contribute to platform decisions across product and engineering boundaries.

Requirements

• Strong backend or platform engineering fundamentals.
• Experience operating data-intensive services or systems backed by machine learning models.
• Clear technical writing and ability to collaborate calmly across disciplines.
• Sound judgment about when to standardize and when a simpler approach is appropriate.

Benefits and work setup

• Full-time, remote-friendly position with working-hours overlap in Asia or Europe.