Full Stack AI Software Engineer

We are seeking an exceptional Full-Stack AI Software Engineer to design, build, deploy, secure, and continuously improve enterprise software and AI-enabled applications. This is a hands‑on engineering role for a highly capable product engineer who can translate complex business problems into secure, scalable, and intuitive technical solutions. The engineer will work directly with business stakeholders in an interactive, iterative development model—rapidly converting ideas into working prototypes, testing solutions with users in real time, and refining functionality until the intended business outcome is achieved.

The successful candidate will combine strong traditional software‑engineering fundamentals with practical experience using modern AI‑assisted development tools, large language models, AI agents, and automation frameworks. The engineer will own applications throughout their lifecycle, including architecture, development, testing, deployment, monitoring, vulnerability remediation, maintenance, modernization, and retirement. Each engineer may be responsible for the health, delivery, and continued evolution of up to three applications at any given time.

• Partner directly with business stakeholders to understand operating processes, identify root problems, define measurable outcomes, and engineer effective technical solutions.

• Translate ambiguous business needs into clear functional requirements, technical designs, user stories, acceptance criteria, and production‑ready software.

• Work interactively with users through rapid prototyping, demonstrations, feedback sessions, and iterative releases.

• Build new applications and enhance existing platforms across the frontend, backend, application programming interface, integration, data, and infrastructure layers.

• Develop intuitive, accessible, responsive, and high‑performing user experiences.

• Design reusable services, components, APIs, workflows, and integration patterns.

• Make thoughtful build‑versus‑buy and configuration‑versus‑custom‑development recommendations.

• Balance delivery speed with security, reliability, maintainability, scalability, and long‑term architectural integrity.

• Use modern AI engineering tools throughout the software development lifecycle to improve development speed, quality, testing, documentation, and maintainability.

• Design and implement AI‑enabled capabilities using large language models, retrieval‑augmented generation, embeddings, vector search, structured outputs, tool calling, multimodal models, and agentic workflows.

• Build AI agents that can securely interact with applications, APIs, databases, documents, and enterprise systems.

• Develop effective prompts, system instructions, context‑management strategies, tool definitions, workflows, and reusable AI skills.

• Evaluate and select appropriate models based on accuracy, latency, security, cost, reliability, and business requirements.

• Implement model evaluations, regression tests, guardrails, human‑review controls, grounding, observability, and fallback mechanisms.

• Identify and mitigate hallucination, prompt‑injection, data‑leakage, model‑bias, unsafe‑output, and unauthorized‑tool‑use risks.

• Measure AI solutions using defined quality, accuracy, safety, performance, adoption, and business‑value metrics.

• Maintain awareness of rapidly evolving AI models, development tools, frameworks, security risks, and engineering practices.

• Own software delivery from initial discovery and architecture through development, testing, deployment, production support, and continuous improvement.

• Write clean, modular, testable, secure, and well‑documented production code.

• Develop…