Staff AI Engineer

Description

The company makes memory and storage products. The team is hiring an experienced AI full stack engineer to build applications where AI is a core feature, both in how software gets built and in the systems that ship.

The team needs more people to support a growing SMAI Data Science group and to extend software support for Technology Development workflows and AI enablement.

The role goes beyond using AI coding assistants. The aim is to cut development and feedback cycles by automating routine engineering work, supporting human decisions, and putting intelligence into both development workflows and delivered applications.

Responsibilities

• Help with platform enablement, architecture choices, code reviews and shared engineering standards.
• Own features end to end: design, build, test, deploy and operate full stack software, including observability and lifecycle support.
• Work with business teams to turn their requirements into scalable solutions.
• Build custom AI agents for task automation, decision support, summarization, multi-step reasoning and guided execution.
• Create prototypes through prompt engineering and vibe coding.
• Build integrations on the Model Context Protocol (MCP) so models, tools and agents share structured context and expose capabilities to LLM-based agents, without hard-coded links between AI components.
• Connect applications to internal and external AI services such as LLMs, embeddings, search and tools through well-designed APIs.
• Harden AI components for 24x7 critical physical manufacturing systems, covering reliability, resiliency, latency, performance, security, permissions, data boundaries, observability and maintainability, and apply retrieval-augmented generation (RAG) systems.
• Use AI tools for code generation, refactoring, test creation and documentation, then check and refine their output and make the architecture, correctness and long-term maintenance calls yourself.
• Gather and analyse requirements to understand software domains, interfaces and characteristics. Write code in programming, scripting and database languages, and support testing, deployment, maintenance and evolution, following the team's standards for code reviews, source control, builds, testing and operations.
• Help shape the roadmap for a platform that processes large data volumes across sites, running distributed systems on Kubernetes.

Requirements

• Solid grounding in full stack fundamentals: object-oriented design, clean code, testing strategies and long-term maintainability.
• Proven record building and running production backend or full stack systems, including API design, service integration and data persistence.
• Ability to design and evolve scalable architectures, weighing performance, reliability, security and developer productivity.
• Experience in cloud-native environments with CI/CD pipelines, containerized deployments and modern operations practices.
• Sound knowledge of relational and non-relational data modeling and storage, and choosing the right tool for each problem.
• A history of owning software end to end, from design through lifecycle support, while working across engineering and business teams.
• Experience with C, ASP.NET, Angular, RESTful APIs, SQL and NoSQL databases, and Kubernetes-based platforms.
• Experience designing and building custom AI agents that go beyond chat interfaces, including developing agent skills.
• AI-native skills: prompt engineering, vibe coding, context window management and chain-of-thought design.
• Experience integrating systems through MCP or equivalent structured agent and tool interfaces, with a firm grasp of prompt design and tool invocation.
• Ability to reason about hallucination risk, failure modes, permissions and guardrails in AI-enabled systems, with hands-on RAG integration experience.
• Strong interest in Kubernetes and cloud-native infrastructure, including running, upgrading and troubleshooting production clusters, and growing your skills in container orchestration, GPU workloads and platform reliability.
• Experience running distributed systems on Kubernetes, with an understanding of message-driven architectures, horizontal scaling, fault tolerance and multi-tenant workloads.
• Preferred: experience using AI-enabled development practices to speed up engineering and raise productivity.
• Preferred: a record of judging AI-generated output critically and refining it to production standard.
• Preferred: experience building interoperable AI systems without hard-coded integrations.
• Preferred: understanding of running AI in critical environments with strict reliability and performance needs.

Conditions

The posting links to information on the right to work.

For US sites, applicants can contact the People Organization for help with the application or reasonable accommodations.

The company bans child labor, complies with applicable labor laws and charges candidates no recruitment fees.

Benefits

• Medical, dental and vision plans available in all locations, so you can choose the cover that fits your family and budget.
• Income protection if illness or injury stops you from working.
• Paid family leave, a paid time-off program and paid holidays.
• Full details are in the benefits guide on the company's careers site.