Role Description We are looking for a Applied AI Engineer to build and operate LLM-powered internal solutions, tools, automations, and customer-facing AI features end-to-end. We are not building AI for the sake of AI, or to follow hype or impress investors. We care about AI that works in real life and solves actual problems. Technology choices and product decisions are not simply handed down from the top. You will have room to shape the solution, challenge assumptions, choose the right tools, and influence the result. - Build and operate LLM-powered internal solutions, tools, and automations end-to-end - Ship customer-facing AI features - Drive technical decisions from design through production rollout - Own systems in production, including monitoring, reliability improvements, and incident response participation - Build and maintain LLM evaluation workflows, including quality/safety checks, baselines, and regression detection - Partner with R&D, product, and security teams - Evaluate emerging AI technologies and patterns, and advocate adoption when justified Qualifications - Strong software engineering fundamentals with hands-on ownership of production systems; Python required - Solid LLM application development experience, including context design, structured outputs, and orchestration - Hands-on experience with LLM evaluations, including experiment design, regression detection, gating, and observability - Experience building and operating backend services/APIs in production - Experience designing multi-service architectures and reliable integrations, including stable service contracts, retries, and failure recovery - Working knowledge of operating production databases, including schema design, indexing, migrations, and backup/restore - Hands-on experience with containerized workloads - Ability to balance output quality, latency, and cost in production AI systems Requirements - Experience with agentic systems or RAG, including evaluation - Experience building lightweight user interfaces - Experience shipping high-adoption internal developer or operations tooling - JavaScript/TypeScript - AWS deployment and operations experience - Experience with runtime isolation and sandboxing for sensitive execution - Experience in B2B SaaS, security, compliance, or data governance contexts Technology we use You do not need to have experience with every tool listed below, but this is the environment we work with now: - Python, uv, FastAPI, PydanticAI - PostgreSQL, Docker, Docker Compose - AWS: EC2, ECR, S3, Lambda - Interfaces and tooling: Streamlit or similar tools, pytest, ruff, pyright, OpenTelemetry Benefits - Fully remote work, giving you the flexibility you need in the modern world - A collaborative environment encouraging you to own your domain and implement best practices - Stable income, benefits, flexible working hours, and opportunities for promotion - Friendly and professional peers, eager to help and help you grow - A multitude of interesting challenges and opportunities

• Lead hands-on technical execution of AI engagements • Transform strategic vision into production-grade autonomous agent systems • Serve as a trusted technical advisor to executive stakeholders • Facilitate workshops to identify high-value use cases • Implement cutting-edge MLOps best practices for reliability and ethics • Deploy sophisticated models within major enterprise ecosystems • Test builder tools and stay ahead of AI advancements

• This candidate will be configuring data pipelines, establishing data ingestion processes, and implementing predictive modeling components that analyze five (or more) years of historical data to generate time- and location-based risk forecasts. • Role includes integration with existing systems and data to ensure seamless data flow and usability within current operational workflows. • Experience with all AI models to validate data integrity, model performance, and system reliability. • Assessing prediction accuracy, ensuring alignment between forecasted and observed patterns, and verifying that outputs are operationally meaningful for command staff and field leadership. • Experience within STRIDE platform. • Build machine learning and deep learning models (e.g., neural networks, LLMs) to address specific business problems. • Fine-tune AI models to ensure high performance, scalability, and efficiency in cloud environments.

• Identify and prioritize high-impact AI use cases across Customer Office teams in partnership with Revenue Operations. • Design and implement AI-driven workflows and agentic solutions across the Customer Office tech stack. • Build and scale automation and intelligence layers on top of Salesforce and the broader GTM stack. • Serve as the AI expert, partnering with Enterprise Systems and Architecture teams to define and enforce data models. • Leverage Customer data to power AI-driven insights and workflows. • Stay ahead of AI and GTM technology trends by rapidly evaluating and testing new tools and approaches.