Principal AI Platform Engineer

🌍 Who we are:
Adaptiq is a technology hub specializing in building, scaling, and supporting R&D teams for high-end, fast-growing product companies in a wide range of industries.

🧩 About the Product:
Our client develops software that helps engineering teams deploy and manage AI workloads in production. The platform simplifies infrastructure operations and supports reliable, scalable services across different deployment environments.

🌟 About the Role:
We are looking for a Senior Software Engineer to develop platform capabilities supporting AI model deployment and operation.
You will combine Python development with hands-on infrastructure engineering, improving the tools and services that help teams bring AI workloads into production. Your work will include performance optimization, automation, and operational reliability.

You will collaborate with other engineers, contribute to technical decisions, and take ownership of your work from design through deployment and ongoing support. The role includes participation in an on-call rotation.

📈 Key Responsibilities:
Develop Python services and tools supporting AI workloads.
Deploy, operate, and scale LLM inference services to meet the needs of active users and production traffic.
Configure and optimize model execution across multiple GPUs and compute nodes.
Build and improve automated deployment and configuration workflows.
Integrate and configure model-serving technologies.
Analyze system performance and improve scalability, resource efficiency, and reliability.
Design tests to evaluate production readiness and identify performance bottlenecks.
Improve monitoring, diagnostics, and recovery processes.
Investigate production issues across software and infrastructure components.
Contribute to architecture discussions, code reviews, and technical documentation.
Collaborate with engineering teams to translate requirements into maintainable solutions.


💻 Required Competence and Skills:
Strong Python development skills and experience building maintainable production software.
Hands-on experience operating LLM inference services in production, supporting active users and real-world traffic.
Practical experience deploying and serving models across multi-GPU configurations and multi-node environments.
Experience configuring and tuning an LLM-serving framework, such as vLLM or a comparable technology.
Practical understanding of GPU memory constraints and how they affect model deployment and execution.
Experience evaluating performance under load and interpreting latency, throughput, and resource usage.
Familiarity with techniques for reducing model memory requirements and improving inference efficiency.
Experience with infrastructure automation and infrastructure-as-code tools.
Strong Linux troubleshooting skills.
Experience supporting production services, including monitoring and incident resolution.
Ability to work independently, assess technical trade-offs, and communicate decisions clearly.
Clear written and spoken English.

➕ Nice to Have:
Experience with distributed systems or large-scale compute environments.
Familiarity with multiple model-serving technologies.
Experience with container orchestration and cloud infrastructure.
Understanding of networking and its impact on application performance.
Experience building tools for resource management, deployment, or operational automation.
Background in AI platforms, developer tools, or infrastructure software.

🚀 Why Us:
- We provide 20 days of vacation leave per calendar year (plus official national holidays of a country you are based in).
- We provide full accounting and legal support in all countries we operate.
- We utilize a fully remote work model with a powerful workstation and co-working space in case you need it.