Founding Engineer - Data & AI

Pennant is growing fast and opening our NYC office (IRL is a must for this role). Come pace the frontier with us for this unique opportunity to join a YC-backed company fresh off the summer batch, and report directly to the Co-Founder/CEO and have tangible impact on our company every single day.

Company Description

Pennant is building AI-native software for corporate governance, starting with proxy voting and shareholder/company engagement.

Institutional investors, public companies and their advisors make consequential decisions using information scattered across filings, policies, research and on the desk conversations. We bring that information together so teams can understand the evidence, apply their own judgment and preserve why they made a decision. We're bringing frontier AI capabilities to enterprise grade offerings used by trillion-dollar decision-makers across capital markets.

Our ambition is a world model for corporate governance: a system that connects institutional knowledge, policies, decisions and outcomes. Getting there starts with reliable data and software customers trust in their daily work.

Role Description

Founding Engineer – AI & Data is an on-site position based in New York, NY. Reports to the Co-founder & CTO; works directly with both founders and domain experts. You’ll be part of the founding Pennant team to design, build, and ship the core AI features of the product. Build and own the data systems that make Pennant useful and trustworthy.

This is a backend- and data-intensive applied AI role. You should be as comfortable debugging a production pipeline and evolving a database schema as evaluating a document-extraction model. You will build on an existing codebase, working with messy filings and customer documents and making the results dependable enough for customers to use. The work includes asynchronous jobs, versioned evidence and safe reprocessing—not just prompts and model experiments.

Your first mandate is one prioritized pipeline and its downstream use. You will establish what good looks like with domain experts, improve the system, and own it in production. As one of our first engineering hires, you will also help shape how we build, test and operate software.

How We Work

We work in person in New York and stay close to customers across the country on-site. We prototype quickly, use AI development tools where they help, and remain responsible for what we ship.

We narrow scope before compromising correctness, permissions or customer trust. We test representative cases and failure paths, observe what happens after release, and flag risks early. Founding engineers have room to make decisions and are expected to make their reasoning understandable to the team.

Qualifications

• Committed to working IRL in NYC
• A builder with a personal and professional portfolio: shipped projects, GitHub repos, hackathon wins, and/or products people actually use
• Strong programming skills in Python and/or TypeScript
• Hands-on experience building with LLM APIs (OpenAI, Anthropic, etc.) and familiarity with embeddings, vector search, prompt design, or agent frameworks
• Experience with document parsing/OCR, information extraction, or financial/legal text
• Strong with evals, fine-tuning, or LLM observability tools
• Cloud infrastructure experience (AWS/GCP), Postgres, and CI/CD
• Prior startup, research, or founding experience
• Proficient with AI coding tools (e.g., Cursor, Claude Code, Conductor, VSCode) to move fast without giving up quality
• Strong grasp of data modeling, APIs, and working with unstructured data
• A product sense for when something is good enough to ship and when it needs another pass
• Clear communicator who can explain technical tradeoffs to non-engineers
• Strong backend engineering, SQL and database fundamentals, with experience operating production services or data pipelines
• Practical experience with asynchronous or distributed processing: idempotency, retries, concurrency and recovery when only part of a job succeeds
• Experience turning messy documents or other imperfect source data into structured information people depend on
• Practical experience shipping model-based systems and improving them through evaluations, user feedback and failure analysis
• Sound judgment about schema evolution, entity resolution, historical records and data provenance
• The ability to become productive in an existing codebase, debug across services and storage systems, and evolve interfaces or schemas without breaking their consumers
• The independence to narrow an ambiguous problem, ask for the context you need and carry the work through production use.