• Design and build data-driven tools that operate on large datasets stored in S3 and Snowflake • Implement pipelines that: • Extract specific columns or datasets from Snowflake • Generate vector embeddings via APIs such as OpenAI • Store and manage embeddings in vector databases like Pinecone • Enable semantic search and similarity-based retrieval • Develop enrichment workflows that: • Query structured data • Use LLM APIs to generate new derived columns • Write enriched results back into Snowflake • Build reusable internal services and SDKs around embedding generation, prompt orchestration, and data augmentation • Optimize performance and cost across AWS infrastructure • Work closely with product and data teams to turn use cases into scalable engineering solutions • Ensure reliability, observability, and maintainability of AI-powered pipelines

• Participate in example meetings • Lead example initiatives • Recruit new team members to example team • Mentor and develop existing team members

• Lead and influence cloud architecture decisions for new platforms and modernization initiatives, with a focus on AWS and hybrid cloud patterns. • Design and deliver cloud‑native and hybrid solutions that support the migration of legacy on‑prem .NET systems to modern, containerized, serverless, or Linux‑based runtimes. • Own Infrastructure as Code (IaC) implementations and automation strategies to ensure repeatable, secure, and scalable environments. • Build and operate production‑grade cloud services, emphasizing reliability, performance, security, and cost efficiency. • Partner with application teams to modernize CI/CD pipelines, deployment strategies, and runtime architectures. • Drive serverless‑first and platform engineering best practices, mentoring engineers and raising the overall cloud maturity of the organization. • Define and document reference architectures, operational patterns, and platform standards. • Support operational excellence, including incident response, root cause analysis, and participation in a rotating on‑call schedule. • Champion change, incident, and problem management practices within a DevOps/SRE‑aligned operating model. • Collaborate across infrastructure, networking, security, and vendor teams to ensure compliant, well‑designed application architectures. • Design and support business continuity and disaster recovery strategies aligned to enterprise availability and resilience goals. • Proactively address security and compliance concerns, ensuring platforms are hardened against evolving cybersecurity threats.

• Implement and deploy AI agents into internal Gatekeeper workflows. • Work directly with internal teams (Product, Marketing, Finance, Sales, Account Management, Operations, Professional Services) to understand processes and identify high-impact AI use cases. • Configure agent behaviour through prompts across different tools, rules and guardrails. • Integrate AI agents with existing systems, data sources and internal tools via APIs, webhooks and integrations. • Use Python for orchestration, data handling, light automation and evaluation. • Test, iterate and refine AI agents based on real usage and feedback. • Monitor deployed agents for accuracy, reliability and business impact, escalating issues where deeper platform changes are needed. • Collaborate with the Senior AI Platform Engineer on agent standards, tooling, observability, governance and ROI. • Document implementations and help establish repeatable internal AI deployment patterns.