Lead Software Engineer

Toshiba Global Commerce Solutions is seeking a hands-on Lead Software Engineer to drive end-to-end solution delivery for major retail platforms, and to make AI-augmented engineering the way our teams build. In this role, you will own hands-on implementation (feature development, technical design, code reviews), engagement leadership (client-facing technical lead, trade-off decisions, mentoring), and operational ownership (delivery sign-off, post-release support) of high-impact solutions, translating business requirements into working software you help build. You will also be the engineering authority on how AI is used across the delivery lifecycle: designing agentic workflows, setting guardrails, measuring impact, and bringing the team along. You will drive Dual-Track Agile processes, using AI to compress the Discovery Track (rapid prototyping and feasibility validation) and to raise quality, traceability, and measurable outcomes in the Delivery Track. The ideal candidate is a senior software engineer who codes daily and treats AI agents as a core part of their toolchain. You have moved beyond personal use of AI assistants to building repeatable, governed, measurable AI workflows that other engineers adopt, from analysis and design to testing, documentation, and code generation, while bringing the technical leadership to drive client engagements forward. You will mentor teams, make critical technical trade-offs, and take full accountability for delivery sign-off and post-release support. This role requires strong retail platform domain knowledge (POS systems, store operations), cloud-native development experience, and deep fluency with generative and agentic AI tools to accelerate delivery while preserving code quality and architectural integrity. You will have the judgment to know when AI output can be trusted and when it cannot, and you will be a key driver of engineering excellence, ensuring solutions are both innovative and operationally robust. Key Responsibilities • Design and operate AI/agentic workflows across the software lifecycle, including requirements analysis, design, prototyping, code generation, test-case creation, specification drafting, code review, documentation, and automated validation, and use them in your own daily development. • Define team standards for AI-assisted development: prompt and context practices, reusable agent skills and instructions, repository conventions, and review expectations for AI-generated code. • Establish guardrails for responsible AI use, including IP and licensing, secrets and data handling, security review of generated code, and client contractual constraints, and ensure ethical compliance across the team. • Build evaluation and validation around AI output (automated tests, specification conformance, static analysis, human-in-the-loop checkpoints) so that speed gains do not erode quality. • Define and report metrics on AI impact, such as cycle time, review turnaround, defect escape rate, test coverage, rework, and cost per outcome, and use them to decide where AI helps and where it does not. • Evaluate, pilot, and recommend AI tools, models, and integrations (IDE assistants, CLI agents, MCP servers, internal automation), considering cost, security, and vendor risk. • Build internal tooling and automation on LLM APIs where it removes recurring toil, such as PR summarization, test generation, release notes, and defect triage. • Own end-to-end solution delivery across Discovery and Delivery Tracks, personally building validated prototypes, contributing to formal designs, decomposing work into deliverables, and shipping accepted technical implementations. • Drive the Discovery Track under Dual-Track Agile by writing AI-accelerated working prototypes and demoing solutions to validate feasibility and align stakeholders before full implementation. • Translate discovery outcomes into delivery backlog items and partner with implementation teams to ensure design intent, code quality standards, and non-functional requirements are preserved throughout delivery. • Contribute to technical design across products and integrations: produce ADRs, OpenAPI interface contracts, data models, sequencing diagrams, migration/rollback plans, and traceability matrices that serve as implementation inputs for both engineers and AI agents, partnering with architects on broader governance. • Serve as the primary technical lead in client engagements: facilitate workshops, present technical solutions, make trade-off decisions, drive approvals, and explain AI-assisted delivery credibly to client stakeholders. • Personally implement critical components and complex features in modern retail platform stacks, set the bar for code quality through your own work, and review and approve deliverables from implementation teams, including AI-generated changes. • Apply and reinforce engineering standards, reusable integration patterns, and non-functional requirements (security, scalability, observability) across client solutions. • Mentor and upskill engineers on AI-assisted development, Dual-Track workflows, specification-driven design, and platform best practices, primarily through pair programming, live demos, code reviews, and example-driven leadership, including when to trust, verify, or reject AI output. • Contribute to platform and product strategy, identifying reusable assets, API-first designs, technical gaps requiring investment, and where AI creates product or delivery leverage. • Own risk analysis and mitigation for technical decisions, including backward compatibility, data integrity, compliance constraints, and AI-specific risks. Must-Have Qualifications • Bachelor’s degree in Computer Science, Engineering, or equivalent experience. • 8+ years of professional software development experience with current, daily hands-on coding and prototyping in modern technology stacks. • Demonstrated daily use of AI coding agents and assistants (e.g., Claude Code, Cursor, GitHub Copilot) for design, coding, test generation, and documentation, with measurable impact on delivery that you can describe with specifics. • Experience designing repeatable AI workflows for a team, such as shared agent instructions or skills, prompt and context libraries, review checklists, and CI-integrated validation. • Working knowledge of LLM fundamentals: context management, tool use and agents, MCP or similar integrations, non-determinism, hallucination risk, and cost and latency trade-offs. • Experience validating AI-generated code through test-first or specification-first approaches, automated checks, and rigorous review. • 5+ years building cloud-native, microservices, or event-driven systems, with experience in Azure or equivalent cloud platforms. • Strong proficiency in technology stacks such as Java/Spring Boot, TypeScript, React/Vue. • Proven experience owning end-to-end solution delivery, including design, implementation, and post-release operational accountability for medium-to-large projects. • Track record of building production code, prototypes, and reference implementations to validate solution feasibility. • Strong experience with REST/OpenAPI, messaging platforms, and relational/non-relational databases (SQL/NoSQL). • Hands-on proficiency with CI/CD, containerization, Docker, Kubernetes, deployment tooling, and automated testing. • Excellent stakeholder communication skills, able to facilitate workshops, present technical solutions, and collaborate across business and engineering teams. • Proven leadership in mentoring engineers, conducting thorough code reviews, and championing engineering best practices across teams. Preferred Qualifications • Experience building with LLM APIs (e.g., the Claude API or Azure OpenAI), including tool use, agents, evals, and prompt caching. • Experience establishing AI governance, security, or compliance practices in an enterprise or client-facing setting. • Experience building in