Python Inference Engineer

Role overview

This position sits within a platform engineering group that operates a Platform-as-a-Service stack focused on edge cloud and AI services. The engineer will develop and operate Python-based inference components that power machine learning workloads delivered from edge infrastructure.

Responsibilities

- Design, build, and maintain Python services that run machine learning inference in production environments - Optimize model serving for latency, throughput, and resource efficiency at scale - Collaborate with platform engineers to integrate inference workloads into edge cloud infrastructure - Profile, debug, and harden inference pipelines running across distributed systems - Contribute to reliability practices, including monitoring, logging, and incident response for AI services

Requirements

- Strong proficiency in Python and modern software engineering practices - Hands-on experience with machine learning inference frameworks and model serving patterns - Familiarity with containerization and cloud-native deployment of Python services - Understanding of performance tuning for latency-sensitive workloads

Benefits and work setup

- Full-time, remote position open to candidates based in Serbia or Cyprus