$162,000 - $243,000 USD yearly
Originally posted 14 October 2026 by the employer.
About the role
This role advances the software ecosystem for large-scale LLM inference on Qualcomm platforms, working across open-source serving systems, distributed runtimes, cloud-native infrastructure, and AI accelerator software. You will contribute to open-source projects such as llm-d and related LLM inference engines while building the integrations required to execute workloads on Qualcomm AI accelerators.
What you'll do
- Contribute features, enhancements, and bug fixes to open-source LLM inference projects, including llm-d, and collaborate with upstream maintainers to upstream Qualcomm-related functionality.
- Develop and enhance inference engine integrations for Qualcomm AI accelerators, addressing device abstraction, runtime integration, memory management, compilation, and performance optimization.
- Design and implement distributed inference capabilities such as prefill/decode disaggregation, KV-cache management, request routing, and tensor, pipeline, or expert model parallelism.
- Integrate LLM inference software with Kubernetes and cloud-native infrastructure, covering scheduling, autoscaling, networking, observability, and lifecycle management.
- Profile, benchmark, and optimize end-to-end inference performance, targeting time to first token (TTFT), inter-token latency (ITL), throughput, memory utilization, and multi-node scalability.
- Diagnose issues spanning model-serving frameworks, distributed runtimes, operating systems, networking, accelerator runtimes, and hardware.
What you'll need
- Bachelor's degree in Computer Science, Engineering, Information Systems, or a related field with 4+ years of relevant experience (or a Master's degree with 3+ years, or a PhD with 2+ years).
- Experience developing production-quality software in one or more of Python, C++, Go, or Rust.
- Strong understanding of at least one area: machine learning or LLM inference systems, distributed systems, AI accelerator or GPU software, cloud-native/Kubernetes infrastructure, or ML compiler/runtime systems.
- Demonstrated software engineering and debugging skills across multiple layers of complex systems.
Nice to have
- Experience with LLM inference runtimes, model-serving frameworks, or distributed inference systems, including attention mechanisms and KV-cache transfer.
- Hands-on experience with llm-d, KServe, Kubernetes Gateway API, Kubernetes operators, or cloud-native AI infrastructure.
- Familiarity with PyTorch internals, torch.compile, Dynamo, Inductor, Triton, MLIR, or related compiler and runtime technologies.
- Knowledge of hardware accelerator software stacks, GPU programming, or custom AI accelerator integration.
- Experience with high-speed networking and distributed communication libraries, including RDMA, RoCE, GPU Direct-style communication, or PCIe.
- History of open-source development, including upstream patch contributions, code reviews, and community design discussions.
Skills: LLM inference, AI accelerators, Kubernetes, KV-cache, distributed systems, model parallelism
More semiconductor jobs: Qualcomm jobs · Santa Clara jobs
First seen in our index 29 days ago, well below the 57-day median for Infrastructure/Platform Software roles.
Infrastructure/Platform Software · Infrastructure Platform
|
Open roles in category
1040
|
Median days since first seen
57 d
|
Category median salary (all employers)
$236k
|
See the full market breakdown ▾Category comparison, skills in demand, and who else is hiring
| Metric | Qualcomm | All employers we track in this specialty (1040 roles · 91 employers) |
|---|---|---|
| Open roles in this specialty | 62 | 1040 |
| Open roles in the wider Software, Firmware & Systems family | 738 | 6700 · 161 employers |
| Median days since first seen | 58 d | 57 d (−1 d vs this employer) |
| Median salary (USD postings) | n/a | $236k |
Skills observed across this category: LLM inference, AI accelerators, Kubernetes, KV-cache, distributed systems, model parallelism
Who's hiring in this category
- NVIDIA · 353 open roles · median 62 d
- Qualcomm (this employer) · 60 open roles · median 59 d
- AMD · 55 open roles · median 37 d
- Graphcore · 47 open roles · median 119 d
- Arm Holdings · 38 open roles · median 16 d
- Cerebras · 36 open roles · median 108 d
How we counted: 1040 open Infrastructure/Platform Software (Infrastructure Platform) roles from 91 employers tracked in the SemiconductorJobs index, counted 13 Nov 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there, and is counted in the wider Software, Firmware & Systems family row. Days are counted from when our index first saw each posting, not from the employer's original posting date.