The company makes retail store solutions used by major brands, and it is the world's installed market share leader in in-store systems.
The role leads end-to-end delivery of solutions for large retail platforms and puts AI-assisted engineering at the center of how the teams work.
You will combine hands-on building with client-facing technical leadership, mentoring, and ownership of delivery sign-off and post-release support.
You will set the engineering direction for AI use across the delivery lifecycle, including agentic workflows, guardrails, impact measurement, and team adoption.
You will run Dual-Track Agile, using AI to speed up discovery prototyping and feasibility checks, and to improve quality and traceability in delivery.
The ideal candidate is a senior engineer who codes every day and uses AI agents as a standard part of their toolkit, and who has built governed, measurable AI workflows that other engineers adopt.
The role calls for retail platform knowledge, including POS systems and store operations, cloud-native development experience, and strong working knowledge of generative and agentic AI tools.
You will judge when AI output can be trusted and when it cannot, and help keep solutions innovative, operationally robust, and architecturally sound.
Responsibilities
Design and run AI and agentic workflows across requirements, design, prototyping, code generation, test creation, specifications, code review, documentation, and automated validation, and use them in your own daily work.
Set team standards for AI-assisted development, covering prompts and context, reusable agent skills and instructions, repository conventions, and review rules for AI-generated code.
Set guardrails for responsible AI use covering IP and licensing, secrets and data handling, security review of generated code, client contract limits, and ethical compliance across the team.
Build testing and validation around AI output, including automated tests, specification checks, static analysis, and human checkpoints, so that faster delivery does not lower quality.
Define and report AI impact metrics such as cycle time, review turnaround, defect escape rate, test coverage, rework, and cost per outcome, and use them to decide where AI helps.
Evaluate, pilot, and recommend AI tools, models, and integrations such as IDE assistants, CLI agents, MCP servers, and internal automation, weighing cost, security, and vendor risk.
Build internal tools on LLM APIs that remove repeated manual work, such as PR summaries, test generation, release notes, and defect triage.
Own delivery across Discovery and Delivery Tracks by building validated prototypes, contributing to formal designs, breaking work into deliverables, and shipping accepted implementations.
Lead the Discovery Track by building AI-accelerated working prototypes and demonstrating them to confirm feasibility and align stakeholders before full build.
Turn discovery results into delivery backlog items and work with implementation teams to keep design intent, code quality, and non-functional requirements intact.
Produce technical design inputs such as ADRs, OpenAPI contracts, data models, sequence diagrams, migration and rollback plans, and traceability matrices that serve engineers and AI agents, and work with architects on wider governance.
Act as the main technical lead in client engagements by running workshops, presenting solutions, making trade-off decisions, securing approvals, and explaining AI-assisted delivery to client stakeholders.
Build critical components and complex features on modern retail platform stacks, and review and approve implementation team output, including AI-generated changes.
Apply engineering standards, integration patterns, and non-functional requirements for security, scalability, and observability across client solutions.
Mentor engineers on AI-assisted development, Dual-Track workflows, specification-driven design, and platform practices, mainly through pair programming, live demos, reviews, and worked examples, including when to trust, verify, or reject AI output.
Help shape platform and product strategy by spotting reusable assets, API-first design opportunities, technical gaps worth investing in, and places where AI adds product or delivery value.
Own risk analysis and mitigation for technical decisions, covering backward compatibility, data integrity, compliance, and AI-specific risks.
Requirements
Bachelor's degree in Computer Science, Engineering, or equivalent experience.
8+ years of professional software development experience, with current daily coding and prototyping in modern stacks.
Daily use of AI coding agents and assistants such as Claude Code, Cursor, or GitHub Copilot for design, coding, test generation, and documentation, with specific, measurable delivery results you can describe.
Experience designing repeatable AI workflows for a team, such as shared agent instructions, skills, prompt and context libraries, review checklists, and CI-integrated checks.
Working knowledge of LLM basics: context management, tool use and agents, MCP or similar integrations, non-determinism, hallucination risk, and cost and latency trade-offs.
Experience checking AI-generated code through test-first or specification-first methods, automated checks, and careful review.
5+ years building cloud-native, microservices, or event-driven systems, including Azure or an equivalent cloud platform.
Strong skills in stacks such as Java/Spring Boot, TypeScript, and React or Vue.
Proven record owning end-to-end delivery, including design, build, and post-release operations, on medium to large projects.
Track record of building production code, prototypes, and reference implementations to test solution feasibility.
Strong experience with REST/OpenAPI, messaging platforms, and relational and non-relational databases.
Hands-on work with CI/CD, containers, Docker, Kubernetes, deployment tooling, and automated testing.
Strong communication skills for running workshops, presenting technical solutions, and working across business and engineering teams.
Proven record mentoring engineers, doing thorough code reviews, and promoting engineering best practices across teams.
Preferred qualifications: experience with LLM APIs such as the Claude API or Azure OpenAI, including tool use, agents, evals, and prompt caching.
Preferred qualifications: experience setting AI governance, security, or compliance practices in an enterprise or client-facing setting.
Preferred qualifications: experience building internal developer tools or MCP servers that connect AI with Jira, GitLab, Jenkins, or Confluence.
Preferred qualifications: expertise in formal or machine-readable specifications such as OpenAPI, UML+OCL, TLA+, or equivalent, used to guide implementation and automated validation of AI output.
Preferred qualifications: experience leading Dual-Track Agile, managing both Discovery and Delivery Tracks, and turning discovery results into actionable backlog items.
Preferred qualifications: retail platform domain knowledge, including POS systems and store operations, is highly desirable.
Preferred qualifications: certifications such as Azure Developer Associate, Azure Solutions Architect, or equivalent cloud credentials.
Preferred qualifications: solid understanding of advanced security practices and compliance requirements in enterprise systems.
Preferred qualifications: experience contributing to platform strategy, reusable assets, and API-first designs.
Conditions
Base salary range: $140,000 to $165,000 per year.
The salary range is a general guide. The final offer depends on factors including the scope of the role, your experience, education and training, work location, and market and business conditions.
Discretionary bonus: up to 8% per year, based on individual and company performance.
Benefits
Group health coverage: medical, dental, and vision.
Employee assistance programs and pre-tax spending accounts.
401(k) plan with company match.
Company-provided life insurance and pet insurance.
Employee discounts.
Paid holidays, paid vacation, and sick and personal days.