Research Engineer-Model Efficiency (Intern) (AI)

Location: Singapore, SG or Austin, US

Company

hirify.global is a technology company focused on Bitcoin mining, AI cloud infrastructure, computing power solutions, and data centers.

What you will do

• Improve the cost and serving speed of AI models while preserving task-relevant quality.
• Implement and adapt published methods including quantization, sparsity, pruning, speculative decoding, MTP, serving-time attention, and KV-cache optimization.
• Develop new model-efficiency optimizations where existing techniques are insufficient.
• Build rigorous evaluation processes using task-level metrics, controlled comparisons, and honest baselines.
• Own and present one well-defined project capable of producing a real result within 3–6 months.

Requirements

• Undergraduate, Master's, or PhD studies in Computer Science, Electrical Engineering, Mathematics, or a related field.
• Ability to commit to a 3–6-month internship; full-time commitment is preferred.
• Strong programming skills in Python and hands-on familiarity with PyTorch.
• Coursework, self-study, or research experience in model efficiency, including quantization, sparsity and pruning, speculative decoding, or serving-time attention and KV-cache methods.
• Solid understanding of transformer internals and rigorous model evaluation practices.
• At least one substantial project, paper, or open-source contribution that can be explained end to end.

Nice to have

• Formal research publication record.
• Achievements in academics, engineering projects, open-source contributions, or programming and algorithm competitions.
• Strong interest in cutting-edge AI efficiency research and ownership of a presentable internship result.

Culture & Benefits

• Inclusive environment that values authenticity and diverse perspectives.
• Open workspaces and a start-up-oriented working environment.
• Opportunities to contribute directly to new projects and systems.
• Autonomy, personal accountability, fast growth, and learning opportunities.
• Training, mentoring, welfare benefits, and developmental opportunities.