19 hours ago
San Jose, CA, USAMid Level
Responsibilities
- Design and maintain backend data pipelines that convert engineering data into structured representations.
- Design schemas and queries for new engineering data types and production-scale retrieval workloads.
- Build AI/LLM components, including natural-language retrieval and agentic workflows.
- Diagnose and resolve reliability and performance issues in distributed batch-processing pipelines.
- Add new engineering data domains to the platform and tune LLM components for accuracy, cost, and latency.
- Collaborate with architecture, verification, and design teams to translate workflow needs into platform capabilities.
Requirements
- Strong Python engineering experience in a large shared codebase with unit, integration, and end-to-end testing.
- Experience with graph databases and/or vector search systems, including schema design and query-performance optimization.
- Experience with LLM-based or agentic systems, retrieval-augmented generation, agent orchestration, tool use, and function calling.
- Familiarity with RTL/HDL and physical-design semantics, including SystemVerilog, Verilog, hardware modeling, module hierarchy, and instantiation.
- Experience with time-series and relational data stores and consistency across multiple database backends.
- Strong written and verbal communication skills.
- Bachelor’s or master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
Tech Stack
Categories
AI ApplicationsData Engineering
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.