Senior Embedded Software Engineer

Senior Embedded AI Engineer – Edge LLM & Inference Systems

Embedded AI | Edge Computing | Machine Learning Inference

Are you ready to bring cutting-edge AI to the edge?

We’re seeking a Senior Embedded AI Engineer to help deploy compact, transformer-based LLMs on real-world embedded platforms. Based in Tallinn, this on-site role challenges you to push the limits of inference performance under tight power, latency, and memory constraints.

You'll be part of a team building next-generation intelligent systems—from optimizing model architectures to deploying them on diverse edge hardware, including ARM, RISC-V, and neural processing units (NPUs).

What You’ll Do:

• Optimize and deploy transformer-based LLMs using embedded ML frameworks (e.g., TFLite Micro, Edge Impulse)

• Perform quantization, pruning, and memory mapping for efficient model execution

• Integrate real-time data pipelines with on-device inference

• Adapt and tune models for hardware-specific acceleration (ARM, RISC-V, NPUs)

• Write performant C/C++ and Python code in embedded Linux environments

• Collaborate with hardware and systems teams to align performance goals with real-world deployment

Your Background:

• Solid experience with edge ML frameworks like TFLite Micro, TVM, or Edge Impulse

• Deep understanding of LLM model compression, optimization, and deployment workflows

• Proficient in C/C++, Python, and embedded Linux systems

• Familiar with real-time data ingestion and memory-constrained processing

Bonus Points:

• Prior work with transformer models in edge or mobile environments

• Familiarity with Neural Network Compiler toolchains (e.g., XNNPack, Glow, Apache TVM)

• Hands-on experience with hardware profiling tools and performance counters

• Experience integrating AI into IoT or robotics systems

• Contributions to open-source embedded AI projects