Engineering Manager (Compiler & Runtime)

Normal Computing Corp.; New York (NY); On-site; USD 210,000 - 320,000; Full time

Job summary

Normal Computing Corp. is seeking an Engineering Manager, Compiler & Runtime in New York to build and lead the core software stack for our accelerator hardware.

You will guide the compiler that translates PyTorch models to hardware, plus the runtime and kernels that execute them. You will hire, mentor, and plan work for a team that will deliver end-to-end software on simulators, FPGA prototypes, and silicon as hardware matures.

Qualifications

• Depth in compilers and runtimes to review designs and trade-offs with senior engineers.
• Experience delivering software against hardware schedules from simulation to bring-up.
• Track record of hiring and mentoring strong systems engineers.

Responsibilities

• Lead and grow the compiler and runtime engineering team from early stage.
• Plan work against hardware program and partner with senior compiler architect.
• Coordinate with hardware, serving and simulation teams to ensure end-to-end delivery.

Skills

Compiler development

Team leadership

Hardware-software co-design

Accelerator work experience

Hiring & mentoring

LLM inference workloads

Simulation to silicon

Tools

FPGA prototypes

Simulators

Job description

• Normal’s hardware runs the most memory-bound parts of large-model inference inside memory itself, rather than shuttling weights to a processor. The software that makes this programmable doesn’t exist yet in any standard form
• As Engineering Manager, Compiler & Runtime, you will build and lead the team that writes the core of it: the compiler that takes PyTorch models to our hardware, the runtime that executes them, and the kernels in between
• This is a people-leadership role on a technical team. You will hire the team, plan its work against the hardware program, and partner with our senior compiler architect, who sets the team’s technical direction. Our chip is pre-silicon, so the team builds against simulators and FPGA prototypes first
• Team Building: Grow the compiler and runtime team from its first engineers, set the hiring bar, and develop each engineer’s growth and career
• Delivery: Turn the Systems Software roadmap into plans, milestones, and staffing for the compiler, runtime, and kernels, and deliver against them. Success means LLMs run end to end on our hardware through PyTorch
• Technical Partnership: Work with our compiler architect so that technical decisions get made, staffed, and finished. Stay close enough to the work to review designs and weigh trade-offs
• Cross-Team Coordination: Coordinate with the hardware team, which owns drivers and firmware, and with the serving and simulation work that depends on the compiler and runtime
• Simulation-to-Silicon Continuity: Keep the compiler and runtime working against simulators, FPGA prototypes, and silicon as the hardware matures, so software development never waits on tapeout
• Engineering Practices: Set up the testing, release, and review practices that make the stack reliable enough to ship to customers

Enough depth in compilers and runtimes to review designs and weigh technical trade-offs with senior engineersExperience managing engineers who build compilers, runtimes, or kernels for accelerators or other non-standard hardwareExperience delivering software against a hardware schedule, from simulation through bring-upTrack record of hiring and mentoring strong systems engineersFamiliarity with state of the art ML compiler stacks and with LLM inference workloadsExperience taking an accelerator software stack from zero to production at a startup or new hardware initiativeExperience with in-memory compute, processing-in-memory, or analog hardware interfacesExperience shipping an SDK or software product to external customers