Summary

You'll lead a cross-functional pod that spans the full stack, from C++ inference engines to JavaScript applications. Your responsibility is to ensure that local AI capabilities ship reliably and perform well across devices. You'll balance hands-on technical work with team coordination, guiding foundation and middleware engineers toward shared goals.

This role is ideal for someone who understands both the low-level challenges of edge AI and the product-facing needs of app developers, and wants to drive the delivery of cohesive, production-ready local AI systems.

Responsibilities

1. Work on deploying machine learning models to edge devices using the frameworks: llama.cpp, ggml, onnx
2. Collaborate closely with researchers to assist in coding, training and transitioning models from research to production environments
3. Integrate AI features into existing products, enriching them with the latest advancements in machine learning
4. Managing a cross functional team (pod) made of middleware (JS), foundation (C++), QA and documentation engineers to produce high quality deliverables
5. Regularly assessing, both qualitatively and quantitatively, our position in the market with regards to similar products or platforms
6. Leveraging the expertise of technical architects to ensure robust architectural choices and code quality
7. Ensuring stable releases by following precise internal release processes

Job requirements

1. Excellent programming skills C++
2. Strong experience with Llama.cpp and ggml inference engines, which facilitates the deployment of models to specific GPU architectures
3. Good understanding of deep learning concepts and model architectures
4. Experience with transformers and LLMs
5. Demonstrated ability to rapidly assimilate new technologies and techniques
6. Has experience managing a small, specialized, cross functional team (pod) of 3-5 people
7. Has a genuine passion for building good products that improve people's lives
8. A degree in Computer Science, AI, Machine Learning, or a related field, complemented by a solid track record in AI R&D

Bonus points if:

1. You have extensive experience with Javascript/Typescript
2. You have experience with AWS, containerization platforms, orchestration, and automated testing suites (Maestro, Appium)
3. You understand the difficulties, nuances and importance of p2p technology
4. You have worked with MLC, TVM or similar frameworks
5. You have experience with Vulkan, CUDA
6. You have productionized models

Skills

• C++
• Communications Skills
• Development
• Team Collaboration
• TypeScript