Senior Platform Engineer: AI Gateway & LLM Infra

Kraken; Argentina; On-site; ARS 122,988,000 - 184,482,000; Full time

Job summary

Kraken is seeking a backend/platform engineer to build and operate the AI Gateway, Kraken's company-wide LLM gateway used by engineers across teams. You will design APIs, SDKs and self-service tooling to onboard researchers quickly while ensuring secure, auditable access and scalable performance.

You will own features end to end, collaborating with Security and SRE to keep latency, cost, and reliability in check, and contribute to engineering practices and documentation across the Dev Platform.

Qualifications

• Backend or platform engineer with production API experience.
• Proficient in Rust, Python or TypeScript with tested code.
• Familiar with LLM APIs, authentication and rate limits.
• Experience with observability, CI/CD, containers and Kubernetes.
• Ability to design clean APIs and own work from idea to production.

Responsibilities

• Build and extend the AI Gateway with new model/provider integrations.
• Design APIs, SDKs and tooling for Kraken engineers to onboard quickly.
• Migrate LLM workloads onto the gateway with minimal disruption.
• Implement access control, key management, and audit logging.
• Instrument latency, errors, token usage and cost for workloads.
• Own features end to end and maintain reliability with SRE.
• Provide documentation and debugging help; gather feedback for roadmap.
• Contribute to code reviews, design docs, and engineering practices.

Skills

Backend engineering

APIs & distributed systems

Rust/Python/TypeScript

Kubernetes / Cloud

Observability & CI/CD

Clear communication

Tools

Rust

Python

TypeScript

Kubernetes

CI/CD

Cloud providers

Job description

Kraken is seeking a backend/platform engineer to build and operate the AI Gateway, Kraken's company-wide LLM gateway used by engineers across teams. You will design APIs, SDKs and self-service tooling to onboard researchers quickly while ensuring secure, auditable access and scalable performance.

You will own features end to end, collaborating with Security and SRE to keep latency, cost, and reliability in check, and contribute to engineering practices and documentation across the Dev Platform.