Agentic Systems Engineer

Kepler • New York City, NY

13d

About The Position

We're building the ground truth platform for AI. Generic tools hallucinate data, confabulate reports, and don't show their work. We made accuracy the only possible outcome: every answer traces to its source, every calculation is reproducible, every insight is defensible. We're starting in finance and building the foundational data layer for anywhere decisions depend on trustworthy data. Kepler was founded by two Palantir veterans (20 years combined) who built core parts of Gotham and Foundry, created Palantir Quiver (the analytics engine behind $100M+ deals with BP and Airbus), led major DoD projects, and served as Head of Business Engineering at Citadel. Kepler is backed by founders of OpenAI, Facebook AI, MotherDuck, dbt, Outerbounds, and others. 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

Requirements

• 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

Nice To Haves

• Financial services experience preferred but not required

Responsibilities

• 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.

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

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed