AI Software Engineer, AI Inference Platform

ElastixAI is an early-stage startup building next-generation AI inference infrastructure. This role focuses on designing and extending the low-level serving stack, including customizing open-source frameworks like vLLM and building model sharding and scheduling logic for proprietary AI accelerators. You will work at the intersection of ML systems, compiler/runtime engineering, and hardware-software co-design.

• Architect, extend, and optimize core components of the AI serving platform for throughput, latency, and scalability.
• Customize open-source serving frameworks (e.g., vLLM, SGLang, TensorRT-LLM) for proprietary model ingestion and accelerator integration.
• Develop efficient model partitioning, scheduling, and memory management strategies for multi-device inference.
• Collaborate with ML engineers on model export and runtime optimization (quantization, graph transforms).
• Work closely with hardware engineers to influence accelerator interface design and performance tuning.
• Build APIs and runtime tools enabling flexible, PyTorch-native model deployment on our infrastructure.
• Profile, debug, and optimize across the full stack — from Python orchestration to C++ kernels and PCIe drivers.

• BS/MS/PhD in Computer Science, Electrical/Computer Engineering, or related field.
• 3+ years of professional experience in systems programming, ML infrastructure, or distributed inference.