Senior AI/ML Frameworks Engineer (AI)

TL;DR

Senior AI/ML Frameworks Engineer (AI): Designing and optimizing high-performance frameworks for running machine learning models on edge devices across iOS, Android, macOS, and Linux with an accent on inference pipelines and hardware acceleration. Focus on architecting efficient frameworks for resource-constrained devices, optimizing CPU/GPU/NPU utilization, and improving runtime performance for LLMs and diffusion models.

Location: Remote (United States)

Salary: $150,000 – $200,000 + Equity

Company

An early-stage, venture-backed AI infrastructure company building tools for on-device AI inference to reduce cloud dependency and improve privacy.

What you will do

• Design and optimize high-performance frameworks for ML models on edge devices across iOS, Android, macOS, and Linux.
• Architect efficient inference pipelines across CPU, GPU, memory, and NPU-based hardware.
• Build cross-platform mobile ML tooling and integrate foundation models such as Whisper, diffusion models, and LLMs.
• Profile, benchmark, and improve latency, memory usage, power efficiency, and runtime performance.
• Collaborate with engineering, research, product, and open-source communities to lower adoption barriers for mobile-native AI.
• Explore model compression, quantization, distillation, and hardware acceleration opportunities.

Requirements

• 5+ years of hands-on mobile development experience, with a strong Android focus.
• Proficiency in Kotlin, Swift, C, or C++.
• Deep understanding of iOS and Android OS-level frameworks.
• Experience profiling and optimizing mobile applications, SDKs, frameworks, or inference engines.
• Strong knowledge of mobile performance constraints including battery life, memory footprint, and latency.
• Familiarity with edge ML frameworks such as LiteRT, ONNX, ExecuTorch, CoreML, or MLX.

Nice to have

• Contributions to popular open-source projects.
• Published mobile apps with meaningful user adoption.
• Knowledge of hardware acceleration tools such as Vulkan, Metal, CUDA, or OpenCL.
• Experience with model compression, quantization, or distillation.
• Technical writing and developer advocacy experience.

Culture & Benefits

• End-to-end ownership over core technical decisions and space to drive R&D initiatives.
• Opportunity to contribute to open-source tooling and have high visibility in company direction.
• Technically rigorous, low-process environment built around autonomy and data-driven decisions.
• Competitive compensation including equity and benefits.