Edge AI Model Optimization Software Engineer (AI)

TL;DR

Edge AI Model Optimization Software Engineer (AI/Embedded): Engineering core optimization technology to enable Generative AI, Transformers, and VLMs to run efficiently on next-generation edge platforms with an accent on quantization and high-performance software architecture. Focus on designing scalable PTQ/QAT workflows, implementing approximation algorithms for bit-exactness, and optimizing toolchain hot paths for resource-constrained hardware.

Location: Guadalajara, Mexico

Company

hirify.global is a global leader in secure connectivity solutions for embedded applications, serving automotive, industrial, IoT, and mobile markets.

What you will do

• Design and implement quantization features and mixed-precision flows for production-grade optimization tools.
• Develop and maintain scalable PTQ (Post-Training Quantization) and QAT (Quantization-Aware Training) workflows.
• Engineer the bridge between state-of-the-art quantization prototypes and production-ready deployment recipes.
• Implement approximation algorithms (range estimation, bias correction, BN-folding) while ensuring bit-exactness on hardware.
• Profile and optimize the toolchain hot paths to meet strict memory and compute-constrained targets.
• Act as a technical liaison between AI Research and Hardware Engineering to guide model accuracy and performance.

Requirements

• MSc or Ph.D. in Computer Science, Electrical Engineering, or Mathematics with a specialization in Machine Learning or Deep Learning.
• Mastery of Python and C/C++ with a strong understanding of memory management and hardware mapping (CPUs/NPUs).
• Proven experience in AI/ML with a deep understanding of CNN and Generative AI (Transformers) architectures.
• Strong hands-on experience with PyTorch, ONNX, and other AI/ML frameworks.
• Experience with quantization workflows and troubleshooting accuracy regressions.

Nice to have

• Experience with hardware accelerators, device-level profiling, and diagnosing memory bottlenecks.
• Familiarity with embedded system constraints regarding latency, power, and memory bandwidth.
• Experience implementing advanced quantization for generative AI (e.g., GPTQ, Smoothquant).
• Knowledge of MLIR or TVM.

Culture & Benefits

• Environment that fosters innovation with access to technology experts and mentors.
• Opportunity to work on pioneering projects shaping the future of AI and edge computing.
• Competitive salary, comprehensive benefits, and a collaborative work environment.
• Strong commitment to diversity, inclusion, and equality.
• Extensive professional development through online and offline learning opportunities.