On-device AI Frameworks Engineer (Staff)

Argmax • New York City, NY

1d • Hybrid

About The Position

Argmax is hiring a Staff Engineer for its On-device AI Frameworks team. The engineer will design, implement, and optimize software frameworks that provide developer-friendly APIs for running advanced inference workloads natively on Apple and Android devices. The role involves close collaboration with engineers and researchers to advance on-device inference technology and support adoption of Argmax SDK, the company’s developer toolkit used by enterprises and developers, including in high-stakes industries such as healthcare. The team works closely with customers and may provide support in a forward-deployed capacity.

The engineer will productionize research prototypes by collaborating with the Applied Research team to turn Python prototypes into production-ready framework features using test-driven development. This work may involve experimentation and benchmarking that contributes to research conference submissions. The role also contributes to SDK and framework design, recommending scalable patterns as supported models and workloads grow, and directly assists enterprise customers with onboarding, technical questions, and feature customization.

The position is based three days a week in the office in Palo Alto, California, or Manhattan, New York. Remote work may be possible by exception for exceptional industry-leading candidates.

Requirements

• At least 3 years of hands-on experience developing SDKs or frameworks for iOS or macOS.
• Fluency in Swift.
• Fluency in profiling and optimizing native applications.
• Familiarity with at least one of Core ML, MLX Swift, LiteRT, ONNX, WebGPU, or ExecuTorch.

Nice To Haves

• At least 5 years of hands-on experience developing SDKs or frameworks for iOS or Android.
• A track record of significant open-source contributions.
• Fluency in Swift, Kotlin, and Python.
• Direct experience with Core ML, MLX Swift, and LiteRT.

Responsibilities

• Turn Applied Research team's Python prototypes into production-ready implementations for AI frameworks using test-driven development.
• Collaborate on experimentation and benchmarking that may contribute to AI research conference submissions.
• Recommend scalable SDK and framework design patterns to support growing models and workloads while minimizing technical debt.
• Work directly with enterprise customer engineering teams during onboarding, answering questions and customizing Argmax features to meet customer requirements.

Benefits

• Top-of-market equity at a fast-growing early-stage startup.
• Performance-based equity refreshers twice a year.
• Palo Alto office offers comprehensive on-site amenities, including chef-catered meals.
• Platinum-tier healthcare with 90% employer contribution, including dependents.
• 401(k) match.
• Quarterly in-person team-building weeks in Palo Alto, California.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed