Company: Qualcomm India Private Limited

Job Area: Engineering Group, Software Engineering

Job Summary

As Datacenter Systems and Solutions Engineer, you own the full arc of AI inference programs on Qualcomm's datacenter AI platform from architectural decisions through production deployment and serve as the technical lead on customer engagements. This role requires expertise across the AI stack, including hardware accelerator behavior, inference serving frameworks, model optimization and distributed system design, combined with the cross-functional leadership to drive complex, ambiguous programs across compiler, runtime, serving and customer engineering organizations.

Minimum Qualifications

- Bachelor's degree in Engineering, Information Systems, Computer Science, or related field and 5+ years of systems engineering or related work experience
- OR Master's degree in Engineering, Information Systems, Computer Science, or related field and 4+ years of systems engineering or related work experience
- OR PhD in Engineering, Information Systems, Computer Science, or related field and 2+ years of related experience

Responsibilities

- Lead the architecture and end-to-end design of AI inference solutions on Qualcomm AI hardware, defining system requirements, interface specifications and performance targets for complex deployments
- Own customer AI engagements as technical lead: translate customer requirements into deployment-ready serving architectures, drive model optimization and validate production readiness
- Drive development and deployment of GenAI and LLM applications, including architecture decisions for fine-tuning, quantization,



speculative decoding and disaggregated serving
- Define and execute benchmarking programs across the hardware and software stack; perform root-cause analysis on complex system-level issues and communicate findings to engineering and customer stakeholders
- Mentor and coach engineers on technical approaches, debugging methodology and best practices; provide leadership on project execution and set transparent expectations across contributors
- Identify and prototype solutions to unmet technical challenges; challenge ingrained practices by introducing approaches drawn from current research and validated against production hardware
- Collaborate across compiler, runtime, serving, model engineering and customer engineering teams to resolve cross-functional blockers and deliver system-level objectives
- Define reusable platform capabilities, tooling and documentation that scale team capacity beyond individual engagements
- Contribute to strategic decisions on model portfolio prioritization, inference stack investment and customer deployment architecture
- Track advancements in AI and ML research and translate techniques relevant to Qualcomm's hardware capabilities into actionable product and solution improvements

Required Skills





- Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow)
- Deep understanding of ML model development, deployment and production inference
- Deep understanding of system performance profiling and parallel computing

Preferred Qualifications

- Master's or PhD in Engineering, Information Systems, Computer Science, Physics or related field
- Advanced understanding of GenAI architectures including transformers, diffusion models, LLMs, large vision-language models and embedding models
- Hands-on experience with inference optimization techniques: speculative decoding, KV cache management, continuous batching and tensor/pipeline parallelism
- Experience fine-tuning and distilling GenAI models at scale; familiarity with RLHF and RLAIF methods is a plus
- Background in compiler optimizations for ML workloads targeting heterogeneous hardware
- Experience designing and operating large-scale distributed AI systems with knowledge of microservice and event-driven architectures
- Proficiency with MLOps practices and ML lifecycle tooling; experience with containerization and automation (Docker, Kubernetes, GitOps) is expected
- Experience with observability and performance analysis for ML pipelines: metrics collection, distributed tracing and capacity modeling
- Track record of leading complex technical programs across large, matrixed organizations
- Experience with open-source development workflows and version control systems (Git, GitHub, GitLab, Gerrit)
- Experience with rack-level orchestration and datacenter automation is a plus

📌 Engineer, Staff (Bengaluru)
🏢 Qualcomm
📍 Bengaluru