Research Scientist / Research Engineer, Inference Systems (AI)

Location: Singapore, Singapore or Austin, United States

Company

hirify.global is a technology company focused on Bitcoin mining, AI cloud infrastructure, computing power solutions, and high-performance computing datacenters.

What you will do

• Research the frontier of inference systems for agentic workloads, large mixture-of-experts models, disaggregated serving, and tiered caching.
• Evaluate which research ideas are relevant to production workloads and define measurements before optimizing.
• Design and implement system-level improvements in the inference serving stack.
• Develop new approaches when existing inference architectures do not meet performance or efficiency requirements.
• Collaborate with the AI Cloud platform team responsible for the production serving stack.
• Produce results strong enough to deploy and publish.

Requirements

• Master’s or PhD in Computer Science, Electrical Engineering, or a related field; exceptional Bachelor’s candidates may also be considered.
• Strong understanding of LLM inference and serving systems.
• Hands-on experience with at least one inference engine, such as vLLM or SGLang.
• Experience combining research with implementation and shipping systems code.
• Strong Python and C++ skills.
• Ability to define reliable measurements and clearly explain what results do and do not demonstrate.

Nice to have

• Distributed serving experience.
• Publications at leading systems venues.
• Significant open-source contributions to inference projects.

Culture & Benefits

• Inclusive environment that values authenticity and diverse perspectives.
• International team working in English across Singapore and the United States.
• Opportunity to contribute directly to AI cloud and digital asset infrastructure.
• Autonomous work, personal accountability, and opportunities for rapid growth.
• Training, mentoring, welfare benefits, and developmental opportunities.