• Design, develop, and maintain AI-powered applications with a strong focus on Agentic AI, AI Agents, and LLM-enabled workflows • Build software services, APIs, and orchestration layers that connect AI models and tools into scalable production solutions • Contribute to the design, training, fine-tuning, evaluation, and deployment of AI models, including large language models and supporting ML components • Develop and optimize data pipelines for model training, retrieval, evaluation, and monitoring • Implement testing strategies, benchmarks, and quality controls to ensure AI systems are reliable, accurate, secure, and performant • Collaborate with AI engineers, software developers, scientists, and product managers to translate business requirements into technical solutions • Participate in the full software development lifecycle: design, implementation, testing, deployment, and monitoring in cloud environments (AWS preferred) • Apply engineering best practices for code quality, documentation, maintainability, and operational excellence • Support experimentation with new AI techniques, frameworks, and tooling, and help mature promising ideas into production capabilities • Stay up to date with advancements in generative AI, agentic systems, multi-modal AI, and cloud engineering.

Role Description Our ideal candidate is a seasoned backend engineer with experience building AI-powered systems (tool calls, evals, etc.) and a passion for creating products and features that really matter to customers. You know how to work with LLM APIs, optimize backend infrastructure, and work closely with not only engineers from other stacks, but also cross-functional partners, from retail to customer support to data. We're looking for someone who loves finding simple, straightforward technical solutions to complex problems. We're looking for a seasoned Back End Software Engineer (Senior or Staff level) to work directly with our GM of New Businesses to build out new AI-powered features across our platform. You'll work primarily in Ruby on Rails to bring brand new products and features to life by integrating with LLMs from vendors like OpenAI, Google, etc. What You'll Do - Design, build, and launch new user-facing features powered by large language models (LLMs) - Own major product initiatives from zero-to-one, in partnership with a small but mighty team - Collaborate deeply with Product and Design to shape new products and features - Integrate with third-party APIs like OpenAI, Google, etc., and explore new model capabilities - Contribute to our codebases in Ruby on Rails - Write maintainable, high-quality code with strong test coverage - Mentor other engineers through code reviews and design discussions Qualifications - 6+ years experience building software products end to end - Deep mastery of either Ruby on Rails or another similar back end language - Demonstrated ability to ship zero-to-one products as a solo engineer or team lead - Experience with OpenAI, Anthropic, or similar LLM providers - Clear communication and collaboration skills across disciplines - Startup experience strongly preferred Nice to Haves - Familiarity with prompt engineering or retrieval-augmented generation (RAG) - Prior work on family-facing or consumer social products Benefits - Competitive Salary + Equity Package - 401K matching - Wellness, learning, and home-office budgets - Health, Dental & Vision Medical Plans - Tremendous autonomy to set the direction of your work - Unlimited PTO - Company holidays on the first Friday of every month (Except November & December) Equal Opportunity Employer Skylight is committed to building a diverse and inclusive team. All qualified applicants will be considered without regard to race, color, religion, sex, sexual orientation, gender identity or expression, age, national origin, disability, protected veteran status, or any other factor protected by applicable federal, state, or local laws. If you’re the best person for the job, we want you on board! Salary Information For Colorado-based candidates, the range being offered for this role is $180-$240K based on experience and for California-based candidates, the range being offered for this role is $180-$240K based on experience.

• Design, build, and deploy production-grade end-to-end AI solutions, including workflow automation agents, RAG pipelines, and copilots embedded in business workflows, and LLM-driven applications • Translate business needs into technical designs and working products to deliver usable, high-impact solutions, not just proofs of concept • Architect and implement AI-assisted data workflows and agentic systems • Build and maintain LLM-enabled services, prompt frameworks, and coding standards • Develop semantic/context layers ensuring AI outputs align with business logic and data models • Design multi-agent workflows, including human-in-the-loop controls • Make pragmatic tradeoffs to ship quickly while maintaining long-term sustainability • Create scalable patterns for prompt design & orchestration, agent-based workflows, and API integrations & data access • Inform architecture decisions for AI systems balancing speed, security, scalability, maintainability, and cost • Help establish engineering standards and best practices for applied AI across the organization • Establish reusable components, frameworks, and templates to accelerate AI development • Integrate AI automation with enterprise systems, APIs, and data platforms • Evaluate and recommend tooling across the stack (models, frameworks, vector stores, orchestration layers) • Define data requirements and, when needed, build or extend data pipelines to ensure AI systems have reliable, production-ready inputs • Design and implement evaluation frameworks to define and track AI system performance, including task success, accuracy, latency, cost, and business impact; establish feedback loops to continuously improve quality, reliability, and cost-efficacy in production environments • Build guardrails and validation layers to reduce hallucinations, enforce structured outputs, and ensure safe system behavior • Establish monitoring and observability across AI systems (performance, usage, cost, latency, failure modes) • Implement modern engineering practices including CI/CD, versioning, rollback strategies, and automated testing • Ensure solutions meet security, compliance, and governance requirements in a regulated environment • Partner with business leaders, operations & service teams, and product stakeholders to shape use cases and turn them into working solutions • Work closely with AI Enablement to refine workflows and improve adoption • Drive fast iteration cycles, quickly moving from idea to working solution to scaled implementation; iterate solutions based on real user feedback and usage patterns

• Lead end-to-end discovery, design, and delivery of Agentic AI solutions that improve customer experience and business performance • Translate customer KPIs into scalable AI use cases and architectures that increase automation, reduce friction, and improve service outcomes • Design integration patterns and data flows that enable seamless orchestration across Genesys Cloud, enterprise systems, and third-party platforms • Drive alignment between business and technical stakeholders to prioritize high-impact AI initiatives and accelerate adoption • Deliver rapid prototypes, POCs, and MVPs using Genesys Cloud AI Studio, virtual agents, and copilots, ensuring a clear path to production scalability • Optimize AI solutions post-deployment through continuous iteration, improving accuracy, performance, and measurable business impact • Influence enterprise AI strategy by advising on architecture, platform capabilities, and long-term transformation roadmaps • Champion responsible AI practices, ensuring solutions meet U.S. regulatory and security standards such as HIPAA and PCI where applicable