Software Engineer II (WFH)

# Senior Software Engineer II - AI Engineering ## About the Role Smartsheet is seeking a **Senior Software Engineer II - AI Engineering** to help build the next generation of AI-powered strategic planning and work execution agents through its SmartAssist intelligent agent platform. In this role, you will work closely with Engineering and AI Platform teams to design, build, and operationalize production-grade AI solutions at enterprise scale. You will focus on **LLM-powered agents, RAG, prompt and context engineering, evaluation frameworks, cloud infrastructure, and AI system architecture** while contributing to both legacy and greenfield full-stack applications. The role also includes mentoring engineers, establishing AI development and governance practices, and collaborating with Engineering, Product, and cross-functional teams. ## Key Responsibilities * Design and build production-grade LLM-powered agents and workflows, including system architecture, data pipelines, and deployment strategies. * Develop and optimize prompts, context engineering approaches, RAG pipelines, and agent reasoning patterns. * Build evaluation frameworks to measure accuracy, hallucination rates, quality, and performance across model versions. * Implement and manage end-to-end AI systems on **AWS, GCP, or Azure**. * Monitor, optimize, and support AI systems, including incident response. * Collaborate with Engineering, Product, and cross-functional teams to translate business requirements into technical AI solutions. * Mentor and guide engineers on applied ML best practices, modern AI development patterns, and production considerations. * Establish best practices and standards for AI development, model governance, and responsible AI. * Evaluate emerging AI/LLM tools, frameworks, and techniques for organizational needs. * Contribute to full-stack applications across both legacy and greenfield environments. * Communicate AI quality findings and technical issues clearly to technical and non-technical stakeholders. * Help establish repeatable methodologies for improving AI system quality and evaluation coverage. ## Required Qualifications * **8+ years of software engineering experience**, including at least **2 years working directly with LLMs in production**. * Hands-on experience with **prompt engineering and context engineering**. * Strong working knowledge of **RAG architectures**, including chunking strategies, embedding models, retrieval evaluation, and failure diagnosis. * Experience building or extending **LLM evaluation frameworks**, including scorers and golden datasets. * Fluency in **agent system design** and ability to engage in architectural tradeoff discussions. * Strong **Python** skills. * Experience working in data-heavy environments such as **Databricks, Delta tables, or equivalent**. * Strong written and verbal communication skills, including the ability to explain complex AI quality findings to technical and non-technical stakeholders. * Strong cross-functional judgment and ability to collaborate across Engineering, Product, and AI Platform teams. * Ability to work effectively in ambiguous situations and structure complex technical problems. * Legally eligible to work in the **United States on an ongoing basis**. * **BS or MS in Computer Science, a related field, or equivalent industry experience**. ## Preferred Qualifications * Experience with **MLflow or similar experiment tracking platforms**. * Familiarity with **CI-integrated evaluation pipelines**. * Experience with **multi-agent orchestration frameworks**. * Prior experience in an **Applied AI or LLMOps** function within a product company. ## Skills & Competencies * Software Engineering * AI Engineering * Large Language Models (LLMs) * Generative AI * Prompt Engineering * Context Engineering * Retrieval-Augmented Generation (RAG) * Agent Systems * LLM Evaluation * Python * Databricks * Delta Tables * Cloud AI Systems * AWS, GCP, or Azure * AI System Architecture * Data Pipelines * Model Governance * Responsible AI * Applied Machine Learning * LLMOps * Cross-Functional Collaboration * Technical Communication * Mentoring and Engineering Leadership ## Success Measures * Deliver measurable and validated quality improvements for at least one SmartAssist agent across defined quality dimensions. * Expand evaluation coverage to address significant blind spots in the existing framework. * Establish a repeatable AI quality improvement methodology that can be applied across the broader team. ## Work Arrangement * **Remote eligible** * **United States** * Teleworking options are available from any registered location in the U.S., subject to role requirements. ## Compensation & Benefits **US Base Salary:** $175,000 - $245,000 USD Benefits include: * Employer-subsidized medical, vision, and dental coverage for full-time employees. * 401(k) match of 50% of employee contributions up to the first 6% of eligible pay. * Monthly stipend to support work and productivity. * Company-sponsored life insurance and short-term and long-term disability coverage for U.S. employees. * 12 paid holidays per year. * Up to 24 weeks of parental leave. * Personal paid volunteer day. * Professional growth and development opportunities, including Udemy online courses. * Company-funded perks, including counseling membership, local retail discounts, and a personal Smartsheet account. ## Company **Smartsheet** ## Equal Opportunity Employer Smartsheet is an Equal Opportunity Employer committed to providing equal employment opportunities to qualified applicants in accordance with applicable laws. Qualified applicants receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, protected veteran or disabled status, or genetic information. Show more Show less