Find jobs
Pricing
Free Resume Checker
Sign in
Sign up
FIND JOBSPRICINGFREE RESUME CHECKERSIGN INSIGN UP
Quickchat AI

Founder Fellow - Applied AI

SalaryNo pay range posted
LocationNew York, NY, US
Work modeon-site
Typeinternship
SeniorityEntry
DepartmentEngineering
Company size51–200 people
First seenOct 8, 2026 · 3d ago
Verified live3d ago
New York law requires most employers to post a pay range.
At a glanceSummarised by Seekless from the posting.
Must have5
Solid programming in TypeScript or Python and comfort with SQL
Hands-on experience building something with LLM APIs that other people used
Care about measurement
Patience with dense documents
The habit of finishing: scoped change, tests, review, merge, and a short note on what you learned
Nice to have6
Governance and finance knowledge are not prerequisites
Experience with information extraction
Experience with document parsing
Experience with financial or legal text
Experience with LLM observability tools
Anything you have shipped on your own: repos, a product with users, a research project with results you can defend
Eligibility1
Availability to work in person in New York for the term
Skills
Google Cloud
Node.js
PostgreSQL
Python
TypeScript
SQL
Prompt Engineering
LLMs
Evals
AI Agents
BigQuery
Generative AI
OpenAI
LangSmith
Pennant · S26
Founder Fellow - Applied AI
The World Model for Corporate Governance
LocationNew York, NY, US
About the role
TypeInternship
VisaUS citizen/visa only
Google CloudNode.jsPostgreSQLPythonTypeScriptSQLPrompt EngineeringLLMsEvalsAI AgentsBigQueryGenerative AIOpenAILangSmith
Apply to this role
About the role
Internship, seasonal with potential to convert to full-time. New York City, in-person required. Reports to the Co-founder & CTO and works directly with both founders and domain experts.
About Pennant
Pennant is a YC-backed company building software for corporate governance, starting with proxy voting and company engagement.
Institutional investors, public companies and their advisors make consequential decisions using information scattered across filings, policies, research and conversations. We bring that information together so teams can understand the evidence, apply their own judgment and preserve why they made a decision.
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.
The fellowship
Make our document understanding measurably better and prove it.
Pennant turns dense public filings and customer documents into structured information that analysts rely on. Every number we show traces back to that step, so the interesting work is not writing the first prompt. It is finding where the system is wrong, deciding whether the fix belongs in code, in the prompt or in the evaluation set, and shipping the change with a regression test that would catch it next time.
You will join a team of two founders and our first engineering hires. Your work goes to customers who use it to make real governance decisions. We will hand you bounded problems with a clear success measure, teach you the filings, and expect you to carry each one through to a merged, tested change.
What you’ll work on
•
Extend our evaluation harness. Add human-reviewed reference cases, measure completeness and consequential errors rather than aggregate agreement, and turn production failures into regression tests.
•
Diagnose extraction failures on real filings: a value read from the wrong table, a figure pulled from the wrong period, an item matched to the wrong record. Trace each to its cause and fix it where it belongs.
•
Build deterministic checks around model output so malformed or contradictory results are caught before anyone relies on them.
•
Run cost and quality experiments across models, prompts and caching, with numbers a founder can make a release decision on.
•
Write small tools for domain reviewers so labeling and spot-checks take minutes instead of hours.
Problems you might tackle
•
A model update raises average accuracy on our reference set but silently drops one field on a class of filings. Find the class, quantify it, and decide whether the update ships.
•
A filing uses a table layout we have never seen. Decide whether to extend the parser, adjust the prompt or add a targeted example, and show the change does not regress the rest of the corpus.
•
Our reviewers disagree with each other on a category of cases. Design the reference set so the ambiguity is explicit instead of averaged away.
What you bring
•
Solid programming in TypeScript or Python and comfort with SQL. Most of our code is TypeScript; Python is welcome for analysis.
•
Hands-on experience building something with LLM APIs that other people used, and a clear account of where it failed and what you did about it.
•
Care about measurement. You reach for a test set and a baseline before you reach for a bigger model, and you distrust a metric you cannot explain.
•
Patience with dense documents. You are willing to read a proxy statement closely enough to know when the model is wrong.
•
The habit of finishing: scoped change, tests, review, merge, and a short note on what you learned.
•
Availability to work in person in New York for the term.
Nice to have
Governance and finance knowledge are not prerequisites; we will teach the domain. Experience with information extraction, document parsing, financial or legal text, or LLM observability tools is useful. So is anything you have shipped on your own: repos, a product with users, a research project with results you can defend.
Our stack
A TypeScript monorepo with NestJS services, Go for some backend services, Postgres and BigQuery on Google Cloud. We use Anthropic and OpenAI models with LangSmith tracing, CI enforces coverage gates, and we use AI coding tools daily.
How we work
We work in person in New York and stay close to customers. 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. Fellows get real ownership of bounded problems and are expected to make their reasoning understandable to the team.
Apply
Send a short note and a link to something you built with a language model. Tell us one specific way it was wrong, how you found out, and what you changed. We would rather read that than a list of frameworks.
Apply to this role
Other roles at Pennant
[### Founding Engineer, Product
Full-time · New York, NY, US · $150K - $250K](https://www.workatastartup.com/jobs/111753)[### Founder Fellow - GTM, Growth & Strategy
Internship · New York, NY, US](https://www.workatastartup.com/jobs/111722)[### Founding Engineer, Data & AI
Full-time · New York, NY, US · $150K - $250K](https://www.workatastartup.com/jobs/111752)
Similar roles
[Avallon AI
AI agents for insurance claims operations
Forward Deployed Engineer
Full-time · New York, NY, US · $150K - $240K](https://www.workatastartup.com/jobs/84939)[Autostep
The P&L for knowledge work
Founding Engineer, ML + Forward Deployment
Full-time · San Francisco, CA, US](https://www.workatastartup.com/jobs/105945)[MadeThis
The autonomous business platform
Founding Engineer, Platform
Full-time · San Francisco, CA, US · $250K - $350K](https://www.workatastartup.com/jobs/105107)
More roles at Quickchat AI
Founding Engineer, Data & AISoftware EngineerFounding Mechanical EngineerFull Stack EngineerFounding Electrical Engineer
Seekless
Seek less: one search across companies' own career pages, instead of a dozen job boards.
Product
Find jobsCompaniesPricingFree Resume CheckerBlog
Legal
AboutPrivacyTermsCookies
© 2026 SEEKLESS. ALL RIGHTS RESERVED.BUILT WITH CARE