Job Description:

Position Overview

The primary responsibility of the Senior Software Engineer (AI-First Development) is to design, orchestrate, and validate software applications built through AI-driven development workflows. This is not an AI-assisted traditional developer role. Rather than writing the majority of code by hand, this role operates within an AI-First Software Development Lifecycle (SDLC) where AI agents serve as the primary producers of code, configuration, and test artifacts. The engineer provides architectural direction, context engineering, human-in-the-loop governance, and final accountability for all delivered software.

The Senior Software Engineer combines deep software engineering fundamentals with the ability to think in systems, design effective agent workflows, and validate AI-generated outputs across security, correctness, performance, and compliance dimensions.

Essential Duties & Responsibilities

• Agent Workflow Design and Orchestration

  • Design, build, and maintain AI agent workflows that produce application code, infrastructure configuration, test suites, and documentation.

  • Decompose complex application requirements into discrete, well-scoped tasks that AI agents can execute effectively within defined boundaries.

  • Select and configure appropriate AI models, agent frameworks, and tooling for each workflow based on task complexity, risk level, and cost considerations.

  • Construct and maintain context stores that provide agents with organizational knowledge, coding standards, architectural patterns, and domain context needed to produce correct and consistent outputs.

  • Author and maintain the agent toolchain, including Skills (SKILL.md) for reusable domain knowledge, hooks for deterministic automation at defined workflow points, and project memory files (CLAUDE.md, AGENTS.md) that provide persistent context across agent sessions.

  • Design subagent architectures that decompose complex workflows into specialized, scoped agents with appropriate tool access, following the principle of least privilege for each agent role.

  • Apply compound engineering practices that systematically capture insights, patterns, and failure modes from each development cycle, encoding them into project memory, skills, and agent configurations so that each unit of work makes subsequent work easier and more reliable.

  • Participate in Mob Elaboration sessions to collaboratively refine requirements, acceptance criteria, and context packages before agent execution begins.

• Verification and Quality Assurance

  • Apply a multi-layer verification framework to all AI-generated outputs, validating functional correctness, security posture, performance characteristics, code quality, and regulatory compliance.

  • Establish and enforce human-in-the-loop (HITL), on-the-loop (OHOTL), and after-the-loop (AHOTL) governance checkpoints appropriate to the risk level of each workflow.

  • Review, test, and approve AI-generated code, ensuring it meets Sands coding standards, architectural guidelines, and security requirements before promotion to production.

  • Design and maintain automated verification pipelines that supplement human review, including test harnesses, static analysis gates, and runtime telemetry.

  • Identify and remediate patterns of agent drift, hallucination, or quality degradation across repeated workflow executions.

  • Implement agent observability and telemetry systems that track agent behavior, tool call patterns, token consumption, and output quality metrics across workflows.

• Application Development and Architecture

  • Architect and deliver full-stack applications across web, API, and data layers using AI-First methodologies as the primary development approach.

  • Define system architecture, data models, API contracts, and integration patterns that serve as the foundational context for agent-driven development.

  • Collaborate with cross-functional teams including product, design, infrastructure, and security to translate business requirements into executable agent workflows.

  • Coordinate with development teams across global locations to ensure consistency in agent workflows, coding standards, and verification practices.

  • Maintain the ability to write, debug, and refactor code directly when agent outputs require manual intervention or when exploring novel architectural approaches.

  • Ensure all delivered applications meet enterprise standards for scalability, maintainability, observability, and operational readiness.

  • Design and build custom MCP servers that expose internal tools, databases, and business systems to AI agents through standardized interfaces, enabling agents to interact with enterprise data securely and reliably.

• Continuous Improvement and Mentorship

  • Evaluate emerging AI models, agent frameworks, MCP servers, and development tools to continuously improve workflow effectiveness and output quality.

  • Mentor team members on AI-First development practices, context engineering techniques, and verification methodologies.

  • Contribute to the evolution of the Sands AI-First SDLC standard, proposing refinements based on practical experience and measurable outcomes.

  • Document agent workflow patterns, prompt libraries, context store structures, and lessons learned to build institutional knowledge.

  • Monitor and optimize token consumption and cost across agent workflows, implementing strategies such as plan mode, context editing, multi-session splitting, and efficient context window management to control operational expenses.

  • Participate in Mob Construction sessions, guiding agent execution in real time and coaching team members on effective orchestration techniques.

• Perform job duties in a safe manner.

• Attend work as scheduled on a consistent and regular basis.

• Perform other related duties as assigned.

Minimum Qualifications

• At least 21 years of age.

• Proof of authorization to work in the United States.

• Bachelor's degree in Computer Science, Software Engineering, or a related field, or equivalent professional experience.

• Must be able to obtain and maintain any certification or license, as required by law or policy. 

• 7+ years of professional software development experience, with demonstrated progression into senior or lead roles.

• 1+ years of hands-on experience using AI-assisted development tools (such as GitHub Copilot, Cursor, Claude Code, Windsurf, or similar) as a core part of the daily development workflow.

• Strong foundational knowledge across at least two major programming ecosystems (for example, .NET/C#, JavaScript/TypeScript, Python, Java, Go), with the ability to evaluate and validate AI-generated code in any language relevant to a given project.

• Working knowledge of relational and non-relational databases, including data modeling, query optimization, and schema design.

• Experience with cloud platforms (Azure preferred, AWS or GCP also acceptable), including deployment, configuration, and cost management.

• Working knowledge of DevOps practices, CI/CD pipelines, and infrastructure-as-code concepts.

• Experience with containerization (Docker) and container orchestration (Kubernetes or similar).

• Demonstrated ability to conduct thorough code reviews, identify defects in AI-generated outputs, and provide constructive technical feedback.

• Excellent written and verbal communication skills, with the ability to articulate technical decisions and trade-offs to both technical and non-technical stakeholders.

• Strong 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 experience.

Preferred Qualifications

• Experience designing multi-agent and subagent architectures using frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel, or custom orchestration layers. Understanding of agent planning, tool use, memory, multi-step reasoning, and scoped tool access patterns.

• Practical experience constructing structured context packages for LLMs, including prompt design, RAG pipelines, context window optimization, project memory files (CLAUDE.md, AGENTS.md), and integration with MCP servers. Understanding of tactical context management strategies such as plan mode, context editing, and multi-session splitting.

• Experience authoring Skills (SKILL.md), configuring hooks for deterministic automation, building custom MCP servers, and assembling agent toolchains that enable repeatable, production-grade workflows.

• Experience implementing human-in-the-loop oversight models, automated evaluation pipelines, and strategies for detecting agent drift or hallucination. Familiarity with agent telemetry, token consumption monitoring, and cost governance across multi-agent workflows.

• Experience with microservices, event-driven architectures, or message-based systems (Kafka, RabbitMQ, Azure Service Bus). Understanding of enterprise integration patterns at scale.

• Knowledge of secure development practices, OWASP guidelines, and experience working within regulated industries (gaming, finance, hospitality, or similar). Understanding data privacy and responsible AI principles.

• Experience with unit testing, integration testing, end-to-end testing frameworks, and automated quality gates. Experience evaluating AI-generated test coverage and identifying gaps.

• Track record of mentoring developers, leading technical initiatives, and driving adoption of new development practices across teams.

Physical Requirements

Must be able to:

• Physically access assigned workspace areas with or without reasonable accommodation.

• Work remotely as necessary.

• Work indoors and be exposed to various environmental factors such as, but not limited to, CRT, noise, and dust.

• Utilize laptop and standard keyboard to perform essential functions of the job.