Senior Backend Engineer, AI Infrastructure - Remote (Europe)

Sowelo Consulting sp. z o.o.; Polska; Remote; PLN 307,000 - 482,000; Full time

Benefits offered by this job

Fully remote

Global team

Equity and ownership

High comp flexibility

Job summary

Sowelo Consulting sp. z o.o. is seeking a Backend Engineer specializing in AI infrastructure to own inference and orchestration layers powering AI features across client platforms.

You will build scalable production systems focusing on latency, reliability, and cost efficiency. Based in Europe, this fully remote role offers a global team, strong ownership, and visible impact. You will design high-performance inference pipelines, optimize caching and batching, and collaborate with ML engineers to

Qualifications

• Proven background in core backend software engineering within production environments (Python, Node.js).
• Experience building high-throughput, low-latency distributed microservices.
• Solid understanding of modern AI inference patterns (LLMs, embeddings, multimodal).
• Familiarity with commercial AI APIs (OpenAI, Anthropic) and self-hosted models.
• Production-focused mindset with emphasis on observability, shipping, and runtime efficiency.

Responsibilities

• Build and operate scalable backend systems that serve AI-powered features in production.
• Design high-performance inference pipelines, orchestration workflows, and service boundaries around ML models.
• Own system health and observability: monitoring, logging, alerting, incident response.
• Optimize latency and throughput with caching, batching, and streaming of responses.
• Collaborate with client and ML engineers to deliver stable, high-efficiency APIs for mobile and desktop apps.

Skills

Python

Node.js

Backend systems

Distributed systems

Performance optimization

Tools

Docker

Kubernetes

Job description

Sowelo Consulting sp. z o.o. is seeking a Backend Engineer specializing in AI infrastructure to own inference and orchestration layers powering AI features across client platforms.

You will build scalable production systems focusing on latency, reliability, and cost efficiency. Based in Europe, this fully remote role offers a global team, strong ownership, and visible impact. You will design high-performance inference pipelines, optimize caching and batching, and collaborate with ML engineers to