Senior Device Engineer

🚨 Hiring: AI/ML Frameworks Engineer

📍 Remote

💰 $150K-$200K + Equity & benefits

I’m partnering with an early-stage, venture-backed AI infrastructure company building the future of on-device AI inference. The team is developing tools that allow developers and enterprises to run powerful AI models directly on consumer devices, reducing cloud dependency, improving privacy, lowering latency, and making AI applications faster and more cost-effective. This is a rare opportunity to work at the intersection of mobile engineering, ML systems, edge inference, and developer tooling, alongside a highly technical founding team with deep experience building production-grade AI systems used at massive scale.

What You’ll Be Working On:

You’ll help design, build, and optimise high-performance frameworks for running machine learning models on edge devices across iOS, Android, macOS, Linux, and emerging hardware platforms.

Key areas of focus include:

• Architecting efficient frameworks for running large-scale ML models on resource-constrained devices.
• Optimising inference pipelines across CPU, GPU, memory, and NPU-based hardware.
• Building cross-platform mobile ML tooling across iOS and Android.
• Working with foundation models such as Whisper, diffusion models, and LLMs for real-time on-device inference.
• Profiling, benchmarking, and improving latency, memory usage, power efficiency, and runtime performance.
• Collaborating with engineering, research, product, QA, and open-source communities.
• Helping lower the barrier to adoption for developers building mobile-native AI applications.
• Defining testing and validation strategies across device types, OS versions, and real-world environments.
• Exploring new opportunities in hardware acceleration, model optimisation, compression, quantisation, and distillation.

Key experience includes:

• 5+ years of hands-on mobile development experience, ideally with a strong Android focus.
• Strong experience with Kotlin, Swift, C, or C++.
• Deep understanding of iOS and Android OS-level frameworks.
• Experience profiling and optimising mobile applications, SDKs, frameworks, or inference engines.
• Strong knowledge of mobile performance constraints such as battery life, memory footprint, latency, and CPU/GPU utilisation.
• Familiarity with edge or on-device ML frameworks such as LiteRT, ONNX, ExecuTorch, CoreML, MLX, or similar.
• Experience building production-grade systems, SDKs, developer tools, or open-source infrastructure.

Bonus Points For:

• Contributions to popular open-source projects.
• Published mobile apps with meaningful user adoption.
• Experience with both Swift and Kotlin.
• Experience with mobile ML frameworks and on-device inference.
• Knowledge of hardware acceleration tools such as Vulkan, Metal, CUDA, or OpenCL.
• Experience with model compression, quantisation, distillation, or runtime optimisation.
• Familiarity with NPU-based devices and custom accelerator optimisation.
• Technical writing, open-source community engagement, or developer advocacy experience.

Why This Role Stands Out:

This is not a typical mobile engineering role. You’ll be joining a small, elite team solving some of the most important infrastructure challenges in AI: how to make powerful models run privately, efficiently, and in real time on the devices people already use.

You’ll have:

• End-to-end ownership over core technical decisions.
• The opportunity to contribute to open-source tooling.
• Space to drive your own R&D initiatives.
• High visibility and direct impact on company direction.
• Exposure to cutting-edge mobile AI, inference engines, model optimisation, and hardware-level performance work.
• A technically rigorous, low-process environment built around autonomy, strong opinions, and data-driven decisions.