About Native Chips
Native Chips (NC) is a US-based company with teams in the US and Cairo, building an AI-augmentedplatform for chip design. We work across proprietary and open-source EDA stacks, applying AI/ML tomake chip design faster and more accessible. We deliver platforms to IDMs and offer self-serve Paa S to design teams worldwide. We're a small, senior team — every hire shapes the product and the company.
The Role
We are looking for a Senior AI Engineer who has shipped real agentic AI products, not demos or prototypes. You will design, build, and harden the multi-agent systems at the core of our platform: orchestration, tool use, retrieval, memory, and sandboxed execution. You will work directly with the founding team and have significant ownership over architecture decisions that shape the product.
What You Will Do
Design and build multi-agent workflows using orchestration frameworks such as Lang Graph, including hierarchical orchestrator/worker architectures and stage-gated execution Build and maintain MCP servers and tool integrations that give agents reliable access to internal and external systems Develop and optimize RAG pipelines: chunking, embedding, retrieval quality, evaluation, and knowledge base management Design memory architectures including ephemeral and persistent memory layers Build robust agent execution environments with sandboxing, isolation, and observability Define evaluation frameworks to measure agent quality, reliability, and regression across releases Collaborate with domain experts to translate complex engineering workflows into agentic capabilities
What We Are Looking For
5+ years of software engineering experience, with 2+ years building LLM-based products in production Proven track record shipping agentic AI systems: multi-step tool use, planning, self-correction, and long-running autonomous tasks Hands-on experience building MCP servers or equivalent tool/function-calling infrastructure Deep practical experience with RAG systems, including retrieval evaluation and failure analysis, not just vector database setup Experience implementing memory systems for AI agents (short-term, long-term, and shared/organizational memory) Strong Python engineering skills, plus experience with containerized deployments (Docker, Kubernetes) Experience with at least one major agent/orchestration framework Comfort working in a fast-moving startup environment with high ownership and direct customer exposure
Bonus Points
Background in chip design, EDA, or semiconductor engineering (RTL, verification, digital design flows) Experience with on-premises or air-gapped enterprise deployments Contributions to open-source AI tooling Experience with fine-tuning, prompt optimization, or LLM evaluation at scale
Why Join Us
Direct impact on product direction and engineering culture from day one Work alongside a senior, founder-led team with deep semiconductor industry experience Cairo-based engineering team with US headquarters; remote-friendly working model Competitive compensation with meaningful stock options for early hires Work on technically substantial problems — not maintenance work
Location: Cairo-based, remote-friendly.