Base Salary
$230k - $260k/yr
Responsibilities
- Build core systems powering Kepler’s AI research platform across backend services, data pipelines, frontend interfaces, and infrastructure.
- Ship user interfaces that let analysts trace values to their original document sources.
- Build extraction pipelines with provenance tagging and verification.
- Improve agent-orchestration failure and retry handling for parallel workflows.
- Create verification rules that cross-check extracted values across sources and surface conflicts with provenance.
- Own features end-to-end and take responsibility for functional areas and architecture as the platform scales.
Requirements
- 3–5 years of experience building production software.
- Strong TypeScript and React experience.
- Backend development experience; Rust experience is not required.
- Experience building systems where correctness matters, such as payments, data infrastructure, or healthcare systems.
- Understanding of distributed-systems fundamentals including concurrency, fault tolerance, retries, and idempotency.
- Ability to work across backend services and frontend components and navigate unfamiliar codebases.
- Strong problem-solving ability, systems thinking, communication, and ownership.
- Experience with production systems and attention to failure modes and correctness.
Benefits
- Comprehensive medical, dental, vision, 401(k), and insurance coverage for employees and dependents.
- Automatic basic life, AD&D, and disability insurance coverage.
- Daily lunch provided in the New York office.
- Development environment budget including a MacBook Pro, monitors, ergonomic equipment, and development tools.
- Unlimited PTO.
- Build Anything budget for tools, libraries, datasets, and infrastructure.
- Learning budget for conferences, courses, and programs.
- Work is conducted together in a New York office.
Tech Stack
Categories
About Kepler
We're building the ground truth platform for AI. AI is great at understanding what you're asking for. It's terrible at giving you answers you can trust. Everyone else is trying to make AI more accurate. We made accuracy the only possible outcome by building a platform that separates what AI does well from what code does well. AI handles the conversation. Code handles the truth. The result is the first AI system that can show its work. We automatically ingest data from scattered sources, structure it into a unified platform, and deploy specialized AI agents that conduct deep research with full transparency. Every insight links back to authoritative sources. Every conclusion reveals its reasoning. Every answer can be defended with complete confidence. We're starting in finance, where being wrong costs millions and speed wins deals, but we're building the foundational data layer for the AI era, applicable anywhere that decisions depend on trustworthy data. We're a team of ex-Palantir engineers who built data infrastructure for the world's most demanding organizations. We've raised from top investors, we're working with partners who need this yesterday, and we're building a small team obsessed with foundational technology. If you want to build the platform that becomes the ground truth for AI, we're just getting started.