Kepler: AI you can trust and verify.

Every AI tool has the same flaw: the model touches the data. It guesses numbers, fabricates sources, and gives you a different answer every time you ask. For the people making million-dollar decisions, that's not a feature gap. It's a dealbreaker.

We built the architecture that makes hallucination structurally impossible. AI interprets your intent. Deterministic code retrieves every figure from source documents. The model never produces a number, so it can't get one wrong. Every output traces to a filing, a page, a line item. Every calculation shows its formula. Every answer is defensible.

Live in production. 950K+ SEC filings. 14K+ companies. 40M+ documents. 27 global markets. Trusted by firms that don't get to be wrong.

The architecture is domain-independent. Finance is first because the pain is sharpest. Healthcare, legal, insurance are next. Same system, new data sources. We're not building a finance product. We're building the verification layer for the entire AI stack.

Founded by Vinoo Ganesh (7 yrs Palantir, Head of Business Engineering at Citadel) and Dr. John McRaven (11 yrs Palantir, created the analytics engine behind $100M+ contracts with BP and Airbus, Ph.D. Physics). Backed by the founders of OpenAI, Facebook AI Research, MotherDuck, dbt, and Outerbounds.

The Role

You'll build the agentic infrastructure that powers Kepler's AI research platform. You'll work on the foundational systems that make autonomous AI agents reliable at scale: distributed execution frameworks that run thousands of agents in parallel, evaluation systems that ensure agent quality, context management that maximizes agent performance, and the ontology and provenance systems that let us trace every number back to its source.

This role is for engineers who want to work at the frontier of AI systems, building the infrastructure that makes agents trustworthy for enterprise-critical decisions.

Within your first 90 days, you will:

• Ship your first production agent system with senior mentorship

• Build and deploy infrastructure that powers real financial research workflows

• See your code enable agents to conduct research at top financial institutions

• Take ownership of a core agentic system from architecture to production

What You'll Do

• Build agent execution infrastructure: Distributed systems that orchestrate and run massive numbers of agents in parallel with reliability, retry logic, and graceful degradation.

• Build evaluation systems: Frameworks that measure agent quality, catch regressions, and ensure agents perform reliably across diverse research tasks.

• Optimize agent performance: Context compression, prompt optimization, model routing, and latency reduction. Make agents faster and smarter.

• Build ontology and provenance systems: The semantic layer that maps concepts to precise definitions and traces every output back to authoritative sources. This is what makes our platform trustworthy.

• Integrate AI into production: Language models powering intelligent research workflows with robust error handling, fallback mechanisms, and cost optimization.

• Own systems end-to-end: Design to production. Services, database optimization, deployment, monitoring.

• Ship with production excellence: Comprehensive testing, monitoring, deployment pipelines. You own reliability for what you build.

What We're Looking For

• 7+ years of software engineering experience shipping production systems at scale

• Backend: Python or Node.js, distributed systems, PostgreSQL, Redis, AWS

• Architecture: Experience designing systems that scale and handle complex workflows

• AI/ML systems: Experience building with LLMs, agent frameworks, or ML infrastructure

• Data: Large datasets, ETL pipelines, knowledge graphs or semantic systems a plus

• Practices: Git workflows, CI/CD, automated testing, observability

• Strong communicator who can discuss technical trade-offs clearly

• Curious about the frontier of AI agents and eager to push what's possible

• Thrives in fast-paced environments with high ownership

• Financial services experience preferred but not required

Don't check every box? Apply anyway. We prioritize problem-solving ability, systems thinking, and drive to build transformative agentic infrastructure.

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 agent system design

• Clear growth path toward technical leadership and system ownership

• Learn by building production agentic systems that power real financial research

Our Technical Stack

• Frontend: React, Typescript, Vite, Tailwind, Radix, TanStack, Zustand

• Backend: Rust, Node.js, Python, PostgreSQL, Redis

• AI/ML: OpenAI, Anthropic, MCP SDK,

• Infrastructure: AWS (S3, RDS), Docker, Temporal, Kubernetes, Dataflow

• Tools: Git, GitHub, Pulumi, Auth0, SharePoint
  

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

• Development environment budget - latest MacBook Pro, multiple monitors, ergonomic setup, and any development tools you need

• Unlimited PTO policy

• "Build anything" budget - dedicated funding for whatever tools, libraries, datasets, or infrastructure you need to solve technical challenges, no questions asked

• Learning budget - attend any conference, course, or program that makes you better at what we're building
  

Our Operating Principles

• Forward-Deployed with Product DNA: We own customer outcomes while building a product company. That means embedding, iterating, and deploying where our customers are. We don't win if they don't win.

• Extreme Ownership: Big vision, shared ownership. If you notice a problem, you own it. Authority comes from initiative, not job titles. Once you step up, you're accountable for the outcome.

• Production-First Engineering: We design for critical workloads from day one. Durable execution, blue/green deploys, automated rollbacks, continuous delivery with end-to-end observability. Every change lands safely and stays resilient under real-world load.

• Trust as the Default: People do their best work when confidence is mutual. We show our work, keep our promises, and flag risks before they bite. Trust isn't an aspiration. It's the baseline.

• Keep Raising the Bar: We block time for training, code-health sprints, and deep-dive tech talks. A sharper team and a cleaner stack pay compounding dividends. Continuous learning isn't a perk. It's part of the job.

Kepler is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind. We are committed to the principle of equal employment opportunity for all employees and to providing employees with a work environment free of discrimination and harassment.