AI Platform Backend Engineer

Tawteen; Muscat; Presencial; OMR 35.000 - 54.000; Jornada completa

Descripción de la vacante

Tawteen is seeking an experienced backend platform engineer to build and run the AI platform backend that governs access to AI models and tools, the infrastructure it runs on, and the AI features built on top of it.

You will implement REST APIs, deploy on Kubernetes with Helm, ensure security, integrate with LLM providers, and help teams integrate with the platform APIs. The role emphasizes production ML engineering, observability, and documentation.

Formación

• Degree in computer science or related field or equivalent experience.
• Proficiency with Python and Go.
• Experience with at least one LLM API (OpenAI/Anthropic/Google).
• Kubernetes, Helm, Argo CD and CI/CD tooling experience.
• Security controls including OAuth/OIDC and secrets management.

Responsabilidades

• Build and maintain backend services and APIs.
• REST streaming in Python or Go.
• Deploy and operate services and AI model servers on Kubernetes.
• Implement authentication, access control and security controls.
• Integrate with LLM providers and vector/HRT models.
• Build retrieval-augmented generation, tool calls and agent features.
• Set up monitoring dashboards and alerts; write runbooks and docs.

Conocimientos

Python

Go

REST APIs

HTTP

Linux

Git

Docker

LLM APIs

OpenAI

Anthropic

Google

Educación

Degree in Computer Science

Herramientas

Kubernetes

Helm

Argo CD

CI/CD

GitHub Actions

GitLab CI

vLLM

Ollama

PostgreSQL

pgvector

Redis

HashiCorp Vault

Prometheus

Grafana

OpenTelemetry

Langfuse

Descripción del empleo

Tawteen is seeking an experienced backend platform engineer to build and run the AI platform backend that governs access to AI models and tools, the infrastructure it runs on, and the AI features built on top of it.

You will implement REST APIs, deploy on Kubernetes with Helm, ensure security, integrate with LLM providers, and help teams integrate with the platform APIs. The role emphasizes production ML engineering, observability, and documentation.