AI SDK & Platform Engineer

I Machines, Inc.; United States; On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Health, dental, vision

Retirement savings plans

Paid time off

Flexible Schedule

Job summary

I Machines, Inc. is seeking an experienced AI SDK Engineer to build a full software platform that lets customers move models from major frameworks to our AI compute engines—from edge to cloud.

You will design a high-performance runtime, craft optimized kernels, and enable end-to-end deployment across devices and platforms. The role requires 5+ years in AI infrastructure or compiler/runtime work, strong C/C++ and Python skills, and hands-on experience with PyTorch, TensorFlow, ONNX, and

Qualifications

• BS/MS/PhD in Computer Science, Engineering, or equivalent.
• 5+ years in systems software, AI infrastructure, compiler/runtime, or embedded AI.
• Excellent C/C++ and Python proficiency.
• Experience deploying AI models on specialized hardware.

Responsibilities

• Build end-to-end AI model deployment pipelines across major frameworks for iMachine hardware.
• Design and maintain a high-performance AI runtime with multi-accelerator support.
• Create optimized kernels for core AI ops (GEMM, attention, conv, KV-cache, quantization).
• Optimize LLM/VLM inference performance including KV-cache and low-precision formats.

Skills

C/C++

Python

Systems software

AI inference

Multi-accelerator

Education

BS/MS/PhD in CS/CE/EE

Tools

PyTorch

TensorFlow

ONNX

LLVM/MLIR

Job description

We’re a fast-paced, fabless semiconductor startup redefining the boundaries of AI through cutting-edge, scalable AI-infused compute architecture. Our mission is to deliver scalable, efficient, and intelligent silicon solutions for the next generation of edge AI, robotics, autonomous systems, and mobile devices. Our leadership team brings together decades of experience in semiconductor innovation, spanning chip architecture, system design, and global business operations. The team includes pioneers behind several generations of groundbreaking compute architectures, experts in software-hardware co-design, SoC and AI development with hundreds of patents in our portfolio as well as leaders of multi-billion-dollar business units at top-tier technology companies.

Position Overview

We are seeking a talented AI SDK Engineer to build the complete iMachines AI software platform that enables customers to take models from popular AI frameworks and deploy them efficiently across the iMachines AI compute engines—from edge devices through near-edge and cloud systems.

Key Responsibilities and Duties

• Build end-to-end AI model deployment pipelines across major frameworks (PyTorch, ONNX, TensorFlow, Hugging Face, etc.) for iMachine hardware.
• Design and maintain a high-performance AI runtime handling model execution, scheduling, memory, and multi-accelerator/multi-chiplet support.
• Create optimized kernels and low-level implementations for core AI ops (GEMM, attention, convolution, KV-cache, quantization, etc.).
• Optimize LLM/VLM inference performance including prefill/decode efficiency, KV-cache, low-precision formats, and serving frameworks like vLLM/llama.cpp.
• Build optimized reference implementations across key AI domains (LLMs, vision, speech, robotics, recommendation, edge AI).
• Develop a full developer SDK with tools for compilation, deployment, profiling, debugging, benchmarking, and performance diagnostics.
• Establish performance benchmarking and regression systems across models, kernels, compiler versions, and hardware platforms.
• Support customer enablement and SDK quality through workload porting, debugging, reference apps, CI/CD testing, and release management

Qualifications and Skills

Successful candidates should possess the following qualifications and skills:

Required Qualifications

• BS/MS/PhD in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
• 5+ years in systems software, AI infrastructure, compiler, runtime, accelerator software, or embedded AI.
• Excellent C/C++ and Python.
• Strong understanding of:
• memory hierarchy
• AI inference
• Experience deploying AI models on specialized hardware.
• Experience with one or more:

Preferred Qualifications

• Experience with RISC-V and/or RISC-V Vector (RVV).
• Experience with LLVM/MLIR compiler development.
• Experience developing compiler backends, custom MLIR dialects, or hardware-specific code generation.
• Experience developing high-performance AI kernels and microkernels.
• Experience with NPU, GPU, DSP, vector, or matrix accelerator architectures.
• Experience with AI quantization and low-precision formats including INT8, INT4, FP8, BF16, FP16, and microscaling formats.
• Experience optimizing LLM/VLM inference, including attention, KV-cache, MoE, and speculative decoding.
• Experience with FPGA, emulation, instruction-set simulation, or cycle-accurate simulation.
• Experience with performance profiling and hardware/software performance correlation.
• Experience with multi-core, multi-accelerator, or multi-chiplet systems.
• Experience taking an AI software stack from prototype to production deployment.
• Experience working directly with customers to deploy and optimize AI workloads.

Why Join Us

• Get in early at a breakthrough deep-tech startup reshaping AI compute
• Work closely with industry innovators and experienced leaders where your work will have a direct impact on the success of the company
• Be part of a mission-driven team building foundational technology for the future
• We balance sharp execution with continuous innovation to push the boundaries
• Competitive compensation, equity, and growth opportunities

Benefits and Perks

At I Machines, Inc., we offer competitive salaries and a comprehensive benefits package, including:

• Health, dental, and vision insurance
• Retirement savings plans
• Paid time off and holidays
• Flexible Schedule

Equal Opportunity Employer

I Machines, Inc., is an equal opportunity employer and does not discriminate based on race, color, religion, gender, national origin, age, disability, or any other legally protected status. All qualified applicants will be considered for employment.