#Software Test Engineer - On-Device AI / Generative AI
About The Position
This role emphasizes on-device AI stability, system-level validation, and end-to-end AI pipeline verification across SoC (CPU, GPU, DSP, and NPU) execution environments, ensuring robust and scalable AI performance on real-world devices. This role targets engineers with a strong foundation in computer science (especially AI/ML) who are passionate about testing and validating cutting-edge generative AI technologies, including LLMs, LVMs, LoRA-based models, and agentic AI workflows. The candidate will play a critical role in driving AI test coverage, automation, and system-level quality, ensuring high reliability, performance, and scalability of on-device AI features in a fast-paced environment.
Requirements
- BS/MS in Computer Science or related field.
- Strong foundation in AI/ML, data structures, and algorithms.
- 1-3+ years of experience in software testing or AI validation (fresh graduates with strong AI/ML and programming fundamentals will also be considered)
- Strong programming skills in Python, Java, and Shell.
- Experience with Linux environments and debugging tools.
- Knowledge of LLMs, LVMs, LoRA, and agentic AI concepts.
- Understanding of AI inference workflows.
- Fast learner and adaptable to fast-paced environments.
- Strong team player with excellent communication skills.
Nice To Haves
- Experience with on-device AI frameworks and automation at scale.
- Familiarity with AI evaluation metrics and performance profiling
- Familiarity with Qualcomm's ML/AI Frameworks - QNN SDK or ML SW development kit is a plus
Responsibilities
- Validate on-device AI solutions across mobile, PC, and automotive platforms, ensuring functionality, performance, and robustness.
- Design, develop, and execute end-to-end validation workflows, including model integration, test framework or test application development, device bring-up, and full system validation on target hardware.
- Validate Generative AI use cases across text, multimodal, and speech pipelines, leveraging techniques such as LoRA/adapters, RAG, and agentic AI workflows, ensuring correctness, robustness, and performance on-device
- Define, expand, and track AI test coverage across features and platforms.
- Identify coverage gaps and develop new test scenarios.
- Monitor coverage metrics, pass rates, and regression trends.
- Develop new and maintain existing automation frameworks and scripts using Python, Java, and Shell.
- Build scalable pipelines for AI validation and regression testing.
- Improve efficiency through reusable tools and automation best practices.
- Validate Generative AI models including LLMs, LVMs (multimodal models), and LoRA-based adaptations
- Analyze model outputs for accuracy, consistency, robustness, and edge-case behavior
- Validate hybrid AI pipelines and RAG-based systems, including retrieval quality and response correctness
- Evaluate agentic AI workflows, including multi-step reasoning, tool invocation, and execution reliability
- Perform log analysis and root cause investigation.
- Conduct stress, performance, and long-duration stability testing.
- Debug system, runtime, and model-level issues.
Benefits
- competitive annual discretionary bonus program
- opportunity for annual RSU grants
- highly competitive benefits package
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
