3 days ago
Santa Clara, CA, USA or San Diego, CA, USASenior / Staff+
H1B sponsor
Base Salary
$162k - $243k/yr
Responsibilities
- Contribute features, improvements, bug fixes, and architectural enhancements to llm-d and other open-source LLM inference and serving projects.
- Develop Qualcomm AI accelerator support, inference engine integrations, device abstractions, runtime integrations, memory management, compilation, and performance optimizations.
- Design distributed LLM inference capabilities including prefill/decode disaggregation, KV-cache transfer, request routing, load balancing, model parallelism, multi-node scaling, autoscaling, and resiliency.
- Develop llm-d deployment capabilities, reference architectures, deployment blueprints, configuration, and operational tooling for Qualcomm platforms.
- Integrate inference software with Kubernetes and cloud-native infrastructure, including scheduling, networking, observability, autoscaling, and lifecycle management.
- Profile, benchmark, and optimize inference latency, throughput, memory utilization, and scalability.
- Diagnose issues across model-serving frameworks, distributed runtimes, operating systems, networking, accelerator runtimes, and hardware.
- Collaborate with hardware, firmware, compiler, runtime, Kubernetes, product, and open-source teams.
- Create technical documentation, examples, reference deployments, and best practices for LLM workload deployment.
Requirements
- Bachelor's degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent practical experience.
- Minimum qualifications include 4+ years with a bachelor's degree, 3+ years with a master's degree, or 2+ years with a PhD in a relevant engineering area.
- Strong software engineering and debugging skills with production experience in one or more of Python, C++, Go, or Rust.
- Strong understanding of machine learning or LLM inference systems, distributed systems, AI accelerator or GPU software, cloud-native/Kubernetes infrastructure, or ML compiler/runtime systems.
- Experience working with complex software systems and debugging across multiple layers of the stack.
- Preferred experience includes LLM serving, distributed inference, llm-d, KServe, Kubernetes Gateway API, Kubernetes operators, PyTorch internals, compiler/runtime technologies, accelerator software, RDMA or RoCE, model parallelism, performance optimization, Kubernetes operations, and open-source development.
- Ability to collaborate across teams and communicate technical concepts clearly.
Benefits
- Annual discretionary bonus program and opportunity for annual RSU grants.
- Competitive benefits package supporting work, home, and personal well-being.
- The posted base pay range is $162,000.00-$243,000.00 annually.
Categories
About Qualcomm
Qualcomm is a public semiconductor company headquartered in San Diego, founded in 1985, that designs and sells wireless chipsets and platforms for mobile devices, automotive, IoT, and networking, notably the Snapdragon application processors and 5G modems. It also licenses a large portfolio of cellular patents to device makers, generating revenue alongside chip sales; its technology underpins many Android smartphones and emerging automotive and edge-compute systems, and it trades on NASDAQ as QCOM.