[Remote] Principal Software Engineer - AI-First Development

Note: The job is a remote job and is open to candidates in USA. Las Vegas Sands Corp. is a leading organization in the gaming and hospitality industry, seeking a Principal Software Engineer specializing in AI-First Development. This role involves directing a small engineering team to design and validate software applications using AI-driven workflows, while providing technical mentorship and ensuring adherence to coding standards and quality assurance processes.ResponsibilitiesDefine, build, and maintain the AI agent workflows the team uses to produce application code, infrastructure configuration, test suites, and documentation, and guide other engineers in extending themDecompose application requirements into discrete, well-scoped tasks that AI agents can execute effectively within defined boundaries, and review task decomposition produced by team membersSelect and configure appropriate AI models, agent frameworks, and tooling for each workflow based on task complexity, risk level, and cost considerations, and set the defaults the team works fromConstruct and maintain shared context that provides agents with organizational knowledge, coding standards, architectural patterns, and domain information needed to produce correct and consistent outputsOwn the team's agent toolchain, including reusable skills, automation hooks, MCP integrations, and project memory files that provide persistent context across agent sessionsApply scoped subagent patterns where appropriate, following the principle of least privilege for tool access, and coach engineers on when multi-agent architectures are warranted versus when simpler workflows sufficeSystematically capture insights, patterns, and failure modes from each development cycle and encode them back into shared context, skills, and agent configurations so that subsequent work becomes more reliableLead collaborative requirement refinement sessions to align the team on acceptance criteria and context packages before agent execution beginsApply and uphold a multi-layer verification approach to AI-generated outputs, validating functional correctness, security posture, performance characteristics, code quality, and regulatory complianceSet the human oversight expectations at governance checkpoints appropriate to the risk level of each workflow, including pre-execution review, in-flight observation, and post-execution audit, and verify the team is operating to themServe as the final reviewer and approver of AI-generated code for non-trivial changes, ensuring it meets Sands coding standards, architectural guidelines, and security requirements before promotion to productionBuild and maintain automated verification pipelines that supplement human review, including test harnesses, static analysis gates, and runtime telemetryIdentify and lead remediation of patterns of agent drift, hallucination, or quality degradation across repeated workflow executionsDefine the team's agent observability practices, tracking behavior, tool call patterns, token consumption, and output quality across workflowsArchitect and deliver full-stack applications across web, API, and data layers using AI-First methodologies as the primary development approachDefine system architecture, data models, API contracts, and integration patterns that serve as foundational context for agent-driven development, acting as the technical authority within the team on these decisionsPartner with cross-functional teams including product, design, infrastructure, and security to translate business requirements into executable agent workflowsCoordinate with development teams across global locations to ensure consistency in coding standards and verification practicesWrite, debug, and refactor code directly when agent outputs require manual intervention or when exploring novel architectural approachesEnsure delivered applications meet enterprise standards for scalability, maintainability, observability, and operational readinessDirect the day-to-day technical execution of a small AI-First engineering team, providing dotted-line technical leadership while the formal manager-of-record sits elsewhere in the organizationEvaluate emerging AI models, agent frameworks, and development tools to continuously improve workflow effectiveness and output qualityMentor team members on AI-assisted development practices, context engineering techniques, and verification methodologies, accelerating the growth of less experienced engineers on the teamContribute to the evolution of the Sands AI-First SDLC standard, proposing refinements based on practical experience and measurable outcomesDocument workflow patterns, prompt and context libraries, and lessons learned to build institutional knowledgeMonitor and optimize token consumption and cost across the team's agent workflows, applying strategies such as plan mode, context editing, and efficient context window managementLead collaborative construction sessions, guiding agent execution in real time and coaching team members on effective orchestration techniquesParticipate in hiring activities for the team, including resume review, technical interviews, and onboarding new engineersPerform job duties in a safe mannerAttend work as scheduled on a consistent and regular basisPerform other related duties as assignedSkillsAt least 21 years of ageProof of authorization to work in the United StatesBachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent professional experienceMust be able to obtain and maintain any certification or license, as required by law or policy8+ years of professional software development experience, including time in senior, lead, or staff positions owning the design and delivery of non-trivial systemsDemonstrated experience providing technical leadership to a small engineering team, including running code reviews, mentoring engineers, and driving delivery without necessarily holding the formal people-manager roleDemonstrated daily use, over the past 6 months or more, of at least one modern AI-assisted development tool such as Claude Code, Cursor, GitHub Copilot, or Windsurf, with the ability to speak concretely about effective usage patterns and failure modesStrong foundational knowledge in at least one major programming ecosystem (such as .NET/C#, JavaScript/TypeScript, Python, Java, or Go) and the ability to read, evaluate, and validate code in additional languages relevant to a given projectWorking knowledge of relational and non-relational databases, including data modeling, query performance, and schema designExperience deploying and operating services on at least one major cloud platform (Azure, AWS, or GCP). Azure experience is a plusWorking knowledge of DevOps practices, CI/CD pipelines, and infrastructure-as-code conceptsDemonstrated ability to conduct thorough code reviews, identify defects in both human- and AI-generated outputs, and provide constructive technical feedback to engineers at multiple experience levelsExcellent written and verbal communication skills, with the ability to articulate technical decisions and trade-offs to both technical and non-technical stakeholdersStrong interpersonal skills with the ability to communicate effectively and interact appropriately with management, other Team Members and outside contacts of different backgrounds and levels of experiencePractical experience constructing structured context for LLMs, including prompt design, RAG pipelines, context window optimization, project memory files (such as CLAUDE.md or AGENTS.md), and integration with MCP servers. Familiarity with tactical context management techniques such as plan mode, context editing, and multi-session splittingExperience authoring reusable skills, configuring automation hooks, building custom MCP servers, or otherwise assembling agent toolchains that enable repeatable, production-grade workflowsPrior experience standing up or leading an AI-First or agent-driven development practice on a team, with measurable outcomes around delivery speed, quality, or costExperience with microservices, event-driven architectures, or message-based systems (such as Kafka, RabbitMQ, or Azure Service Bus), and an understanding of enterprise integration patterns at scaleKnowledge of secure development practices and OWASP guidelines, and experience working within a regulated industry such as gaming, finance, healthcare, or hospitality. Understanding of data privacy and responsible AI principlesExperience with unit, integration, and end-to-end testing frameworks, and the ability to evaluate AI-generated test coverage and identify gapsCompany OverviewFounded in 1990, Las Vegas Sands is the preeminent developer and operator of world-class integrated resorts that drive valuable business and leisure tourism in the regions where we operate. It was founded in 1990, and is headquartered in Las Vegas, Nevada, USA, with a workforce of 10001+ employees. Its website is https://www.sands.com.