View on Hacker News
Roles
Compensation
USD 230000 - 260000
$230K-$260K + equity
- Salary period
- yearly
- Location basis
- New York, NY
- Equity
- Equity
Benefits
- Equity
Tech stack
Required
Nice to have
Location
New York, NY, USA
Work setup
- Employment
- full-time
- Level
- Senior
- Remote policy
- Onsite; In-office NYC.
- Remote scope
- onsite
Role details
Responsibilities
- Build a Source-explorer UI to trace any value back to its exact origin in the original document
- Build an extraction pipeline for a data source with provenance and verification from day one
- Develop an agent orchestrator that handles partial failures so one bad extraction does not block parallel work
- Create verification rules to cross-check values across multiple sources and surface conflicts with provenance on both sides
Requirements
- 5 years production experience
- Strong in TypeScript/React
- Comfortable in backend work
- Distributed systems basics: concurrency, fault tolerance, retries, idempotency
Application
Apply via the Ashby job link or email eddie.hammond@kepler.ai.
- GitHub
- not required
- Cover letter
- not required
- Apply flow
- ats
Company context
We’re building the trust layer for AI in high-stakes industries.
- Product
- AI trust layer; research platform for buy-side analysts
- Industry
- trust layer for AI in high-stakes industries
- Stage
- startup
- Funding
- Backed by founders of OpenAI, Meta AI Research, MotherDuck, dbt Labs.
Contact
eddie.hammond
eddie.hammond@kepler.ai
Description
We’re building the trust layer for AI in high-stakes industries. LLM orchestrates (decides what data to gather, what to compute, how to structure output), but the model never touches the data itself. Every actual value flows through deterministic code pipelines with provenance metadata back to source. Verification loops cross-check outputs before users see them. What you’d build: Source-explorer UI that traces any value back to its exact origin in the original document; extraction pipeline for a data source we don’t yet handle, with provenance and verification from day one; agent orchestrator that handles partial failures so a bad extraction from one source doesn’t block parallel work; verification rules that cross-check values across multiple sources and surface conflicts with provenance on both sides. Stack: Rust backend (orchestration, extraction, computation), TypeScript/React frontend, PostgreSQL, AWS. Model-agnostic, currently Claude + GPT. Looking for 5 years production experience, strong in TypeScript/React, comfortable in backend work. Distributed systems basics: concurrency, fault tolerance, retries, idempotency. In-office NYC.
Similar jobs
-
Loading similar jobs...