Pattern Cutting Jobs in California (NOW HIRING)

Job Summary:
Qualcomm is a leading technology innovator focused on enabling next-generation AI experiences. The role of Sr Software Engineer, AI Tools involves developing and implementing cutting-edge tools and solutions for state-of-the-art AI across various technology verticals, with responsibilities including graph optimization, pattern matching, and cross-functional collaboration.
Responsibilities:
• Implement new ONNX graph optimization passes under technical guidance from senior engineers. Work spans pattern matching, dead code elimination, op fusion, reshape/transpose simplification, and layout transforms.
• Extend existing passes to handle new operator patterns, edge cases, and opset variations.
• Write rewrites that follow established compiler engineering practices for clarity, modularity, and testability.
• Write match logic that identifies specific subgraph shapes. This means inspecting op types, attributes, tensor shapes, and producer chains.
• Implement rewrites that transform matched patterns. The rewrites need to preserve graph correctness and any metadata that downstream stages depend on, such as quantization information.
• Reuse existing graph traversal and rewriting utilities rather than reimplementing common operations.
• Write unit tests that exercise new passes against synthetic and real ONNX models. Use IR-level diff checks to confirm transformations produce the expected graph.
• Validate transformations end-to-end using ONNX Runtime. Compare numerical outputs of the pre- and post-optimized models against tolerance thresholds.
• Maintain and extend test fixtures as optimization coverage grows.
• Work closely with engineers on the optimizer team to ramp up on the codebase. Learn how compiler-style optimizations are designed and reviewed in production.
• Coordinate with quantization and model preparation engineers. Understand how optimizer output flows into the rest of the deployment pipeline.
Qualifications:
Required:
• Bachelor's degree in Computer Science, Engineering, Information Systems, or related field and 2+ years of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
• Master's degree in Computer Science, Engineering, Information Systems, or related field and 1+ year of Hardware Engineering, Software Engineering, Systems Engineering, or related work experience.
• PhD in Computer Science, Engineering, Information Systems, or related field.
• Bachelor's degree in Computer Science, Engineering, or related field and 4+ years of Software Engineering, ML Engineering, or related experience.
• Master's degree in Computer Science, Engineering, or related field and 3+ years of relevant experience.
• PhD in Computer Science, Engineering, or related field and 2+ years of relevant experience.
• 2+ years in ML systems, model optimization, or inference engineering.
• Proficient in Python in large, typed codebases.
• Strong written and verbal communication.
• Comfortable operating across compiler, research, and partner-facing teams.
Preferred:
• Working knowledge of graph concepts: intermediate representations, graph traversal, pass-based optimization, pattern matching, and fixed-point iteration.
• Familiarity with the ONNX format, operator semantics, and opset versioning.
• Comfortable with graph algorithms — DFS/BFS, topological sort, basic dataflow analysis.
• Exposure to ONNX Runtime, PyTorch, or another ML framework for model inspection and validation.
• A working sense of model quantization is a plus.
• Strong written and verbal communication. Comfortable asking questions, seeking feedback, and learning quickly from code review.
• Experience using agentic coding tools such as GitHub Copilot, Cursor, Claude Code, Codeium, or similar AI-assisted development tools to improve coding productivity and problem-solving.
Company:
Qualcomm designs wireless technologies and semiconductors that power connectivity, communication, and smart devices. Founded in 1985, the company is headquartered in San Diego, USA, with a team of 10001+ employees. The company is currently Late Stage.