Senior AI Gateway Engineer - Low-Latency Backend

The Briefed; San Francisco (CA); On-site; USD 196,000 - 294,000; Full time

Benefits offered by this job

Market-leading compensation

Equity compensation

Work-from-home setup budget

Conferences & growth

Job summary

Vercel is seeking a Senior Software Engineer on the AI Gateway Team to design, enhance, and scale the AI Gateway platform—a unified API layer providing access to AI models from providers like OpenAI, Anthropic, and Google. In a high-concurrency role, you will build low-latency systems with automatic fallbacks and unified billing/analytics.

You will work with TypeScript and backend distributed architectures to ensure production reliability and scalable integrations, collaborating with product

Qualifications

• 5+ years of professional software engineering experience building backend systems, APIs, or cloud platforms.

Responsibilities

• AI Gateway Platform Architecture: design, implement, and scale unified API endpoints, rate limiting, caching, and dynamic failover.
• Low-Latency High-Throughput Engineering: write modular TypeScript/JavaScript for high-volume AI inference with low latency.
• Provider & Model Integrations: integrate new LLM providers and models into a single developer-agnostic API.
• Open-Source & Developer Ecosystem: contribute to open-source tooling, including the Vercel AI SDK and ecosystem packages.
• Analytics & Platform Features: build features from telemetry, including unified billing metrics and usage analytics.
• Production Reliability & Operations: ensure high availability with automatic fallbacks and circuit breaking.

Skills

TypeScript

Node.js

High concurrency

AI/ML integration

Open-source

Remote collaboration

Job description

Vercel is seeking a Senior Software Engineer on the AI Gateway Team to design, enhance, and scale the AI Gateway platform—a unified API layer providing access to AI models from providers like OpenAI, Anthropic, and Google. In a high-concurrency role, you will build low-latency systems with automatic fallbacks and unified billing/analytics.

You will work with TypeScript and backend distributed architectures to ensure production reliability and scalable integrations, collaborating with product