Note: The job is a remote job and is open to candidates in USA. EnCharge AI is building energy-efficient AI compute systems with a full-stack platform spanning silicon, firmware, drivers, compilers, runtimes, and AI model enablement. The Technical Program Manager will lead embedded software programs from architecture and silicon bring-up through validation and customer deployment, coordinating cross-functional teams, schedules, risks, and hardware-software integration.
Responsibilities
- Own end-to-end program management for embedded software workstreams: device drivers, firmware, boot-loaders and board support packages for EnCharge accelerators
- Build and maintain integrated program schedules that align embedded software milestones with chip tape-out, silicon bring-up, board bring-up, and customer/OEM delivery dates
- Partner closely with embedded software, ASIC/hardware, platform and validation teams to define scope, sequence dependencies, and track execution against plan
- Identify, track, and drive resolution of cross-team risks and blockers (e.g., silicon errata affecting driver behavior, toolchain dependencies, host OS/driver compatibility)
- Drive silicon bring-up and platform enablement, including early firmware, boot flows, device initialization, memory management, command submission, interrupts, power management, and hardware/software integration
- Run the program's operating cadence: planning, standups, milestone reviews, retrospectives tuned to what a hardware-coupled software team actually needs, not generic ceremony
- Drive execution across geographically distributed engineering teams and external partners as needed
- Help build the program management function like process, tooling, and reporting
Skills
- 8+ years of technical program or project management experience, with a meaningful portion spent on embedded software, drivers, firmware, or low-level systems software
- Direct experience coordinating software programs tightly coupled to hardware (silicon bring-up, board bring-up, or similar), ideally in AI/ML accelerators, semiconductors, robotics, or a related hardware-software domain
- Background in Linux kernel driver development processes, JTAG/lab-based debug workflows, or hardware validation methodologies
- Experience with FPGA simulation and emulator environments like Zebu, Veloce, Palladium
- Strong understanding of areas such as:
- Embedded firmware
- Device drivers
- SoC/accelerator architecture
- Memory and DMA
- Interrupts and command queues
- Boot and initialization
- Hardware/software interfaces
- Performance and system-level debugging
- Track record of managing complex, multi-team schedules with hard external dependencies (tape-out dates, partner deliverables, customer commitments) and keeping them honest
- Strong risk management instincts — you find the thing that's going to break the schedule two months before it does
- Excellent written and verbal communication; able to flex between engineering detail and executive summary
- Experience with AI accelerators, GPUs, NPUs, DSPs, or other heterogeneous compute architectures
- Experience with silicon bring-up and early hardware/software co-development
- Experience with firmware for custom accelerators or SoCs
- Experience working across firmware, driver, compiler, and runtime teams
- Experience with simulation/emulation environments used for pre-silicon software development
- Experience with Linux kernel, embedded Linux, RTOS, or low-level systems software
- Experience managing external engineering partners or vendors
Company Overview
Company H1B Sponsorship