AI SDK & Platform Engineer

About Our CompanyWe’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 OverviewWe 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 DutiesBuild 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 managementQualifications and SkillsSuccessful candidates should possess the following qualifications and skills:Required QualificationsBS/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 Linux development experience.Strong understanding of:computer architecturememory hierarchyparallel computingAI inferenceruntime systemsExperience deploying AI models on specialized hardware.Experience with one or more:PyTorch – ONNX - TensorFlow/TFLite - ONNX Runtime – ExecuTorch - llama.cpp - vLLM TensorRT – IREE - TVM – XNNPACKPreferred QualificationsExperience 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 UsGet in early at a breakthrough deep-tech startup reshaping AI computeWork closely with industry innovators and experienced leaders where your work will have a direct impact on the success of the companyBe part of a mission-driven team building foundational technology for the futureWe balance sharp execution with continuous innovation to push the boundariesCompetitive compensation, equity, and growth opportunitiesBenefits and PerksAt I Machines, Inc., we offer competitive salaries and a comprehensive benefits package, including:Health, dental, and vision insuranceRetirement savings plansPaid time off and holidaysProfessional development opportunitiesFlexible ScheduleEqual Opportunity EmployerI 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.