Senior ML Engineer: LLM Inference & Systems Orchestration

NeuReality; Poland; Remote; PLN 240,000 - 300,000; Full time

Job summary

NeuReality is seeking a Senior Machine Learning Engineer to build and integrate LLM-based systems with a strong focus on production readiness, end-to-end workflows, and performance optimization. The role centers on creating robust integration across the AI platform and optimizing prefill/decode, throughput, and latency to deliver reliable services.

The position emphasizes hands-on work on integration flows, system orchestration, and Python tooling for multi-tenant management and caching

Qualifications

• Candidates should have experience with Python and ML systems.
• Strong focus on production readiness and end-to-end workflows.
• Experience integrating components across AI platforms.

Responsibilities

• Build end-to-end integration flows across the AI inference pipeline (serving, orchestration, APIs, infra).
• Design and optimize LLM inference workflows, including prefill and decode stages.
• Improve system throughput, latency, and interactivity.
• Write production-grade Python components and integrate them into the platform.
• Shape system-level logic such as hardware selection and execution strategies.
• Integrate models, services and APIs into cohesive end-to-end pipelines.

Skills

Python

LLM systems

Job description

NeuReality is seeking a Senior Machine Learning Engineer to build and integrate LLM-based systems with a strong focus on production readiness, end-to-end workflows, and performance optimization. The role centers on creating robust integration across the AI platform and optimizing prefill/decode, throughput, and latency to deliver reliable services.

The position emphasizes hands-on work on integration flows, system orchestration, and Python tooling for multi-tenant management and caching