Research Engineer, Algorithms

Normal Computing Corporation • Palo Alto, CA

1d

About The Position

Normal Computing is an applied AI company working on foundational hardware and software for the semiconductor industry, AI infrastructure, and broader computing systems. The Research Engineer, Algorithms will develop computational methods that enable efficient large language model inference on Normal's in-memory hardware. Rather than adapting standard GPU kernels, the role rethinks how operations such as attention, memory access, and long-context decoding should work when computation occurs inside memory.

The engineer will identify which parts of LLM workloads suit in-memory execution, design numerical methods that map to the hardware's physical behavior, and validate these methods using simulators and FPGA prototypes before testing on silicon. This is a hardware-software co-design position: algorithms and hardware are developed in parallel, and the engineer will help shape architectural decisions. The role also involves building evaluation frameworks and benchmarks, translating workload insights into hardware constraints and opportunities, rapid prototyping as hardware evolves, and optimization at both gate and algorithmic levels.

Requirements

• Deep understanding of large-model inference, including attention mechanisms, KV cache, long-context decoding, and memory bandwidth constraints.
• Experience with inference optimization, such as quantization, sparsity, kernel fusion, or memory-efficient attention.
• Familiarity with stochastic systems, probabilistic methods, numerical analysis, or analog computation.
• Experience implementing algorithms close to hardware, beyond high-level frameworks.
• Ability to reason from first principles about what a novel computing substrate can do efficiently.
• Track record of taking ideas from theory to working implementation on real hardware.
• Strong programming skills in Python and at least one systems language.
• Collaborative ability to work across hardware, architecture, and software teams.

Nice To Haves

• PhD in machine learning, applied mathematics, physics, electrical engineering, or a related field.
• Exposure to analog or mixed-signal systems, in-memory compute, or non-von-Neumann architectures.
• Experience working on hardware that did not yet exist when you joined.
• Publications or open-source work in efficient inference, stochastic algorithms, or novel computing.

Responsibilities

• Develop algorithms for LLM inference workloads running on in-memory hardware and demonstrate measurable improvements through simulation and, eventually, silicon.
• Work with hardware and architecture teams to shape what the chip can compute natively.
• Design numerical methods that exploit thermal noise and analog dynamics.
• Build evaluation frameworks and benchmarks to characterize algorithm behavior on hardware or in simulation.
• Translate insights about model workloads into constraints and opportunities for hardware design.
• Prototype and iterate rapidly as hardware evolves from simulation to silicon.
• Optimize performance at both the gate and algorithmic levels.

What This Job Offers

• Job Type: Full-time
• Education Level: No Education Listed