Full Stack Engineer

Full Stack Engineer at Kepler

Location: New York, NY (in-office)
Compensation: $230K - $260K + equity

INTRODUCING KEPLER

The Problem: High-stakes industries are falling behind on AI adoption. Their workflows can't afford wrong answers. And AI can't be trusted to give right ones because of hallucinations. The barrier isn't that the models aren't smart enough. It's that no one can verify what they produce. The fix isn't a better model, it's a trust layer: every output traceable, every calculation auditable, every answer reproducible.

What Kepler Is: Kepler is the agent harness — the infrastructure layer that wraps around AI models to make their outputs reliable, traceable, and verifiable. The model is a replaceable component. The harness is the product.

In Kepler's architecture, the LLM orchestrates — it decides what data to gather, what to compute, how to structure the output. But every actual data point, every extracted value, every calculation flows through deterministic code pipelines. The LLM never touches the data itself. Every value carries provenance metadata back to its exact source. Every computation is auditable and reproducible. Verification loops cross-check outputs before users ever see them.

We started in finance because the stakes are highest and the tolerance for error is zero. We've built a finance research product that lets analysts pull comparables, build models and research filings. Every number traces back to the source, every time.

The architecture — provenance, deterministic computation, verification — applies anywhere trust in AI output matters: chemicals, legal, healthcare. Models are commoditizing fast. The trust layer is what's missing and the market is massive.

The Team: The founding team spent a combined 40+ years at Palantir building large-scale data infrastructure. Our CTO created Palantir's first AI platform and built the analytics engine behind $100M+ contracts. Our founding engineers led Foundry's core systems — Ontology, Fusion, Workshop, FoundryML. Our CEO built and scaled a data company to $15M ARR before selling it, then became Citadel's first Head of Business Engineering. Backed by founders of OpenAI, Meta AI Research, MotherDuck, dbt Labs and Square as well as PebbleBed, Company Ventures and Mantis VC firms.

What You'll Own:

You'll build core systems that power Kepler's AI research platform. You'll work across the stack: backend services that orchestrate AI workflows, data pipelines that process billions of data points, and the infrastructure that financial professionals rely on for million-dollar decisions.

In the first few weeks you might:

• Ship the UI for a source explorer that lets users trace any value back to its exact origin in the original document
• Build a new extraction pipeline for a data source we don't yet handle — with full provenance tagging and verification integrated from day one
• Redesign how our agent orchestrator handles failures and retries so that a bad extraction from one source doesn't block the rest of a parallel workflow
• Add verification rules that cross-check extracted values across multiple sources and surface conflicts with full provenance on both sides

In the longer term, you'll be given ownership of whole functional areas, from extending our platform to a new industry to leading new architecture as our infrastructure scales. You'll consistently own features end-to-end.

How We Work:

We're a close team, working together in an office in New York. We use AI tools heavily — Cursor, Claude Code, whatever makes us faster. Fluency is assumed. Our users are analysts at firms where a wrong number costs real money. The feedback loop on what you ship is hours, not quarters. The pace is startup-fast but the engineering bar is high.

Who You Are:

• 3-5 years building production software
• Strong in TypeScript/React. Comfortable in backend work — our backend is Rust, but we don't require Rust experience. Strong engineering fundamentals matter most
• You've built systems where correctness matters — payments, data infrastructure, healthcare, anything where a wrong output has consequences
• You understand distributed systems basics: concurrency, fault tolerance, retries, idempotency
• You're a quick learner and are as comfortable in a codebase you wrote as one you're reading for the first time
• You care what the analyst does with what you shipped, not whether the code was clever

Our Technical Stack:

• Backend: Rust — agent orchestration, data extraction, computation pipelines
• Frontend: TypeScript, React — the analyst workspace and verification interfaces
• Data: PostgreSQL, plus direct integrations with official data sources
• Infra: AWS
• AI: Model-agnostic by design. Currently uses Claude and GPT. The model is the replaceable part

Mentorship & Growth:

Direct mentorship from engineers who built Palantir's core systems. Weekly 1:1s with senior engineers who've architected enterprise-scale distributed systems. Deep architectural reviews and guidance on system design.

Benefits:

• Comprehensive medical, dental, vision, 401k, insurance for employees and dependents
• Automatic coverage for basic life, AD&D, and disability insurance
• Daily lunch in office
• Latest MacBook Pro, multiple monitors, ergonomic setup
• Unlimited PTO policy
• 'Build anything' budget