AI Researcher (Efficient AI)

Location: Hybrid in Santa Clara, California, United States

Salary: $84.13–$91.34 USD per hour

Company

hirify.global is a global technology corporation developing products and platforms across home appliances, media, vehicles, and eco solutions.

What you will do

• Research, prototype, and implement methods that improve AI model efficiency, inference performance, and deployment on constrained devices.
• Optimize LLMs, SLMs, VLMs, multimodal models, and agentic workloads across post-training, inference, and deployment workflows.
• Develop and evaluate compression techniques including PTQ, QAT, pruning, and low-rank approximation.
• Address long-context inference and KV-cache compression challenges for reasoning and agentic applications.
• Implement efficient architectures and inference optimizations such as MoE, SSMs, speculative decoding, constrained decoding, and kernel-level optimization.
• Build experimental pipelines, run standardized benchmarks, and contribute to publications, technical reports, open-source releases, and IP submissions.

Requirements

• M.S. or Ph.D. in Computer Science, Computer Engineering, Machine Learning, Mathematics, or a related technical field.
• Research or engineering experience in machine learning, efficient AI, model optimization, or AI systems.
• Strong Python programming skills and experience with PyTorch or a comparable deep learning framework.
• Hands-on experience with LLMs, SLMs, VLMs, multimodal models, or generative AI systems.
• Ability to read research papers, implement technical methods, run experiments, and communicate results clearly.
• Strong written and verbal communication skills for reports, presentations, demonstrations, and technical documentation.

Nice to have

• Publications in reputable machine learning or systems venues.
• Experience with llama.cpp, GGUF, vLLM, SGLang, TensorRT-LLM, or related inference and deployment systems.
• Experience with PTQ, QAT, LoRA, distillation, instruction tuning, DPO, OPD, RLVR, or reasoning-oriented adaptation.
• Experience with low-level kernel implementations, on-device acceleration, multi-agent systems, or hardware/software co-design.
• Familiarity with MoE, SSMs, hybrid attention, or Looped Transformers.

Culture & Benefits

• One-year contract with potential extension based on business needs and performance.
• Collaboration with experienced researchers in LG's Emerging Technology Lab.
• Opportunity to contribute to research publications, open-source projects, and intellectual property.
• Contractors are eligible for relevant benefit programs offered through partner agencies.