Looking for a telecommunication/networking expert to help us implement the inference of AI models on programmable network nodes in different 5G/6G network settings: The workload for the target AI application will need to be distributed on a group of networking nodes (e.g., switches, SmartNICs, base stations), having heterogeneous hardware architecture.

• Define the industrial constraints on B5G/6G KPIs, such as latency, resource footprint, bandwidth, and for different types of evolutionized networks related to RAN, WAN, LAN, MEC, etc.
• Help to realize the customized implementation of AI models on a distributed group of heterogeneous hardware of telecommunication devices (e.g., switches, SmartNICs, base stations).
• Adjust aforementioned customized implementations for different networking protocols (e.g., IPv6, Ethernet, TSN, HTTP, etc).
• Help to design scalable scheduling, orchestration, and dynamic resource allocation algorithms, required to integrate aforementioned distributed AI implementations in various network settings.
• Lead the technical validation and prototyping with early adopters.
• Collaborate on grant writing, product roadmap, and tech strategy.
• Hire and mentor future engineers and researchers as the team grows.

• Based in Germany, with a valid Niederlassungserlaubnis or German citizenship.
• A Master's or PhD in Computer Science, Electrical Engineering, or related fields in telecommunication and networking.
• Strong understanding of the 5G/6G stack system hierarchy, from radio access to packet processing.
• Experience with energy efficiency, sustainability, high-throughput, and other impactful design techniques and goals.
• Experience with distributed computing and orchestration techniques in the edge-to-cloud network settings.
• Proven ability to build systems end-to-end: from prototype to deployable demo.
• Fluent in English; German is a bonus.
• A basic background in the following fields:

Machine Learning:

• Structure of DNNs, LLMs, or other AI models for embedded / edge devices.
• Quantization, pruning, knowledge distillation, or other optimization techniques for ML.

Hardware Design:

• Design and synthesis of AI accelerators for FPGAs or custom ASICs.
• Circuit-level optimization, High-Level Synthesis (HLS), or RTL design experience.

Non-paid job at the moment, equity share at the time of founding the company is considered.