AI Research Residency (In-Memory Compute)

Location: On-site in New York, USA

Salary: $150K annually

Company

hirify.global is an applied AI company developing foundational hardware and software for the semiconductor industry, critical AI infrastructure, and systems computing.

What you will do

• Develop inference algorithms for in-memory hardware, focusing on attention, memory access, long-context decoding, and efficient LLM execution.
• Design numerical methods that exploit thermal noise and analog dynamics in in-memory compute systems.
• Build evaluation suites and benchmarks for algorithms running in simulation and on real hardware.
• Translate model workload insights into constraints and opportunities for hardware and architecture teams.
• Prototype and iterate across simulators, FPGA prototypes, and silicon as the hardware evolves.
• Drive an original technical investigation, produce reproducible research code, co-author a paper, and present findings at the company-wide research colloquium.

Requirements

• Currently pursuing or recently completed a graduate degree (MS or PhD), or equivalent research experience, in machine learning, applied mathematics, physics, electrical engineering, computer science, or a related field.
• Working understanding of large-model inference, including attention mechanisms, KV cache, long-context decoding, and memory bandwidth constraints.
• Exposure to inference optimization such as quantization, sparsity, kernel fusion, or memory-efficient attention, or to stochastic systems, probabilistic methods, numerical analysis, or analog computation.
• Strong Python skills and experience with a systems language such as C++, Rust, or similar, or with implementing algorithms close to hardware.
• Experience turning a research idea into working, reasonably reproducible code.
• Ability to reason from first principles about what a novel computational substrate can do efficiently.
• Strong written and verbal communication skills.
• Bias toward ownership and self-direction, with comfort working in an ambiguous and fast-moving startup environment.

Nice to have

• Publications or other evidence of a strong research track record.
• Exposure to analog or mixed-signal systems, in-memory compute, or non-von-Neumann architectures.
• Publications or open-source work in efficient inference, stochastic algorithms, or novel computing.
• Experience working on hardware that did not yet exist when joining a project.
• Experience writing papers, theses, or technical reports and presenting technical work to a live audience.

Culture & Benefits

• Work as part of a small, hand-picked residency cohort with a dedicated research mentor.
• Collaborate directly with researchers and engineers developing in-memory inference hardware and algorithms.
• Work in a fast-moving, well-funded startup environment with rapid iteration from ideas to hardware results.
• Build published and presented research through a paper and a company-wide colloquium.
• hirify.global is committed to equal employment opportunity, diversity, inclusion, and reasonable accessibility accommodations.