On-device AI Frameworks Engineer (Staff)

Job details

Work model

Not provided by source

Salary

Not listed by source

Location

Manhattan, NY

What the role asks for

Parsed by MeritLog from the employer’s own posting. The full description follows below.

Job description

We are looking for a Staff Engineer to join our growing On-device AI Frameworks team at Argmax! In this role, you will design, implement and optimize software frameworks that expose developer-friendly APIs to run state-of-the-art inference workloads natively on Apple and Android devices. You will collaborate closely with industry-leader engineer and researcher colleagues, advancing the frontiers of on-device inference technology and accelerating its market adoption. AI Frameworks are at the core of Argmax SDK, our flagship developer toolkit trusted by Enterprises and developers in high-stakes industries such as healthcare. Argmax is a customer-obsessed team and we work very closely with them, sometimes in forward-deployed capacity. Responsibilities • Productionize research prototypes: The Applied Research team will come to you with a Python prototype that provides the blueprints for a new feature (example) for one of our AI Frameworks. You will collaborate with them in turning this standalone prototype into a production-ready implementation in a test-driven development fashion. This collaboration may include experimentation and benchmarking that leads to top-tier AI research conference submissions (example). • Contribute to SDK and Frameworks design: As the number of supported models and workloads grow, you will see around corners and recommend scalable design patterns to absorb the code growth while minimizing technical debt. • Support Enterprise customers: You will directly work with the engineering teams of Enterprise customers during their onboarding journey. This could range from a Q&A session to customizing an Argmax feature to fit a particular customer requirement. Qualifications • 3+ years of hands-on experience in SDK or Frameworks development 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 Preferred Qualifications • 5+ years of hands-on experience in SDK or Frameworks development for iOS or Android • Track record of significant open-source contributions • Fluency in Swift, Kotlin and Python • Direct experience with Core ML, MLX Swift and LiteRT Perks • Top-of-market equity at a fast-growing early-stage startup with a unique mission • Performance-based equity refreshers twice a year • 3 days a week in the office from Palo Alto, CA or Manhattan, NY • Palo Alto office offers comprehensive on-site amenities, including chef-catered meals • Remote possible by exception for industry leader exceptional candidates • Platinum-tier healthcare with 90% employer contribution, including dependents • 401(k) match • Quarterly in-person team-building weeks in Palo Alto, CA About Argmax AI applications are scaling in user adoption at unprecedented rates. The infrastructure is crumbling: - Spinner wheels are back in fashion - The most sensitive types of user data are uploaded to the cloud and occasionally leaked - Spiky demand leads to infrastructure capacity crunch and underutilization at the same time Argmax is building the critical infrastructure required to bring real-time AI workloads to the edge: - Autoscaling instantly and infinitely - Private and compliant by design - Reliable beyond even the multi-cloud platforms The hardest part: We are directly migrating cloud workloads to the edge, without compromising accuracy that our customers work so hard to achieve. This is a hard core technology problem and we built the mission-driven team with a long-term vision to make on-device the default way to build AI applications. Join us if this sounds like you and you have 3+ years to stake!