Edge Inference Engineer at Liquid AI optimizing machine code for resource-constrained devices. Implementing inference kernels and collaborating with ML researchers on new model architectures.
Responsibilities
Implement and optimize inference kernels for CPU, NPU, and GPU architectures across diverse edge hardware
Develop quantization strategies (INT4, INT8, FP8) that maximize compression while preserving model quality under strict memory budgets
Contribute to llama.cpp and other open-source inference frameworks, including new model architectures (audio, vision)
Profile and optimize end-to-end inference pipelines to achieve sub-100ms time-to-first-token on target devices
Collaborate with ML researchers to understand model architectures and identify optimization opportunities specific to Liquid Foundation Models
Requirements
5+ years of experience in systems programming with strong C++ proficiency
Embedded software engineering experience or work on resource-constrained systems
Understanding of ML fundamentals at the linear algebra level (how matrix operations, attention, and quantization work)
Experience with hardware architecture concepts: cache hierarchies, memory bandwidth, SIMD/vectorization
Contributions to llama.cpp, ExecuTorch, or similar inference frameworks (nice-to-have)
Experience with Rust for systems programming (nice-to-have)
Background in custom accelerator development (TPU, NPU) or work at companies like SambaNova, Cerebras, Groq, or Google/Amazon accelerator teams (nice-to-have)
Quantitative degree (mathematics, physics, or similar) combined with engineering experience (nice-to-have)
Benefits
Competitive base salary with equity in a unicorn-stage company
We pay 100% of medical, dental, and vision premiums for employees and dependents
401(k) matching up to 4% of base pay
Unlimited PTO plus company-wide Refill Days throughout the year
Technical Communications & Research Intern at HII's DIICE assisting Air Force digital transformation projects. Involves technical writing, project coordination, and stakeholder communication.
Materials Developer focused on seasonal developments of high - performance trim materials at Arc'teryx. Collaborate with cross - functional teams to drive product success and sustainability in the supply chain.
Materials Developer I focusing on technical developments in high - performance materials. Joining Arc'teryx's team to enhance supply chain goals and product success.
Operations Engineering Support 2 responsible for troubleshooting and repairing manufacturing equipment at Celestica. Engaging in complex testing and maintenance efforts whilst ensuring quality standards.
Acting as authority for safe work permitting and process improvements in a manufacturing facility. Supporting technical training and monitoring permit requests at the site.
Electrical Test Technician responsible for hands - on testing of batteries and electronic devices at EnerSys. Operates instrumentation, generates reports, and ensures testing compliance.
Project Developer at Aula Energy managing renewable energy projects in Australia. Oversee project development from identification to construction commencement in a hybrid working environment.
Mobile Developer developing mobile applications and implementing automated testing. Collaborating with teams to enhance user experience through high - quality solutions.
Senior Computer Vision Algorithm Developer at Nanit conducting AI solutions research in Computer Vision and machine learning. Develop performance - driven production algorithms for innovative parenting technology.