• Own Technical Direction and Architecture • Set the technical direction for AI systems - including shared AI SDKs, guardrails, evaluation frameworks, feedback systems, and agentic workflow infrastructure • Own architecture and technical strategy for complex backend and AI platform systems, from design through production • Lead technical design for ambiguous, cross-functional initiatives - evaluating tradeoffs, aligning stakeholders, and driving implementation • Evaluate and select technologies with a bias toward what ships well and scales sustainably • Build and Operate AI Systems • Write production code as a hands-on individual contributor - this is not a role that delegates implementation to others • Design and operate LLM-powered systems: RAG pipelines, agentic workflows, evaluation infrastructure, guardrails, and model observability • Own end-to-end reliability of AI systems from design through structured output delivery • Define quality benchmarks, evaluation frameworks, and feedback loops to continuously improve AI output accuracy and system reliability • Champion AI-Native Development • Champion and embed AI-native development practices and tools (e.g., Cursor, Augment) to achieve significant productivity gains across the team • Foster a culture of rapid iteration, high velocity, and quality - including guiding the effective use of AI code generation • Bring strong, informed opinions about how to get the most from AI-assisted development while maintaining reliability and correctness • Lead and Grow the Team • Mentor engineers, raise the quality of technical decision-making, and help the team execute with consistency • Establish coding standards, review practices, and architectural documentation that scale as the team grows • Help define what "good" looks like for a team building at speed without sacrificing quality • Partner with recruiting to build and grow the team • Collaborate Cross-Functionally • Work closely with engineering managers, product, design, and QA to translate requirements into executable technical plans • Participate actively in design reviews and roadmap discussions with grounded, implementation-level perspective • Handle most cross-team conflicts and technical decisions autonomously

• Design, build, and ship production-quality backend services, APIs, and AI platform components used across multiple engineering teams • Build and integrate LLM-powered systems such as RAG pipelines, AI SDKs, evaluation workflows, guardrails, prompt/tool orchestration, and model observability • Improve the reliability, scalability, observability, and operational quality of production AI systems • Build internal tools, frameworks, automation, and documentation that improve developer productivity and AI capabilities • Participate in code reviews, design reviews, debugging, incident response, and operational support • Contribute to technical design for complex projects, including evaluating tradeoffs and proposing pragmatic implementation plans • Partner with product, design, and engineering teams to translate platform needs into well-designed technical solutions • Help identify and reduce technical debt, reliability risks, and friction in the software development lifecycle • Collaborate with Staff and senior engineers to establish reusable patterns and raise engineering standards • Use agentic coding tools and LLM-assisted development as a primary part of your workflow — this is how the entire team operates • Critically evaluate AI-generated code for correctness, edge cases, and regressions — shipping quality output regardless of how it was produced • Contribute to the team's evolving practices around AI-accelerated development and testing

• Build and ship production-quality implementations of data normalization, schema mapping, validation, enrichment, and distribution pipelines for a net-new intelligent data warehouse • Write clean, well-tested, performant code across backend services, data pipeline logic, and API integrations • Take end-to-end ownership of features from design through deployment, with accountability for correctness and reliability in production • Work closely with Staff engineers to shape the architecture of a modern, AI-native data warehouse serving institutional financial clients • Bring thoughtful input on schema design, normalization approaches, and API patterns - and execute those decisions with precision • Identify and raise technical risks early; propose and implement solutions rather than waiting to be directed • Use agentic coding tools and LLM-assisted development as your primary workflow - this is how the entire team operates • Critically evaluate AI-generated code for correctness, edge cases, and regressions - shipping quality output regardless of how it was produced • Build and maintain data validation checks, monitoring, and observability tooling that keeps pipelines trustworthy at scale • Participate in on-call and production support, diagnosing and resolving data quality issues quickly and thoroughly • Write and maintain clear technical documentation for the systems you build

• Design and ship the data normalization, schema mapping, validation, enrichment, and distribution pipeline for a net-new intelligent data warehouse • Write production code as a hands-on individual contributor - this is not a role that delegates implementation to others • Take technical ownership from architecture through deployment, with accountability for reliability, performance, and correctness • Partner with a small seed team to define the end-to-end architecture for an AI-native data warehouse serving institutional financial clients • Bring opinionated decisions on schema design, normalization strategies, API exposure patterns, and data distribution approaches • Evaluate and select technologies with a bias toward what ships well and scales sustainably • Design and implement the evaluation framework that makes AI-generated outputs trustworthy in high-stakes financial data contexts • Build cross-model comparison tooling, deterministic validation checks, and human-in-the-loop review workflows • Contribute to shared AI evaluation infrastructure that can serve as a foundation across multiple products • Use agentic coding tools and LLM-assisted development as your primary workflow - this is how the entire team operates • Bring strong opinions about how to get the most from AI-assisted development while maintaining quality and reliability • Set coding standards, review practices, and architectural documentation that will scale as the team grows • Help define what "good" looks like for a team building at speed without sacrificing quality • Mentor engineers and provide technical guidance as the team expands