Agentic Systems Engineer - AI Research Platform

Location: On-Site | Founding Team: Palantir Veterans | Backed By: OpenAI, Facebook AI Founders.

Build the Infrastructure for Autonomous AI Research

You will architect the core intelligent systems that power autonomous AI agents conducting deep research for enterprise-scale decision-making. Founded by engineers who built core components of Palantir's platforms and backed by the founders of OpenAI and Facebook AI, we're solving a critical problem: professionals in financial services spend 60-70% of their time manually gathering data instead of analyzing it.

Our platform automatically ingests dozens of sources (SEC filings, expert calls, alternative data) and deploys AI agents that conduct deep research while creating interactive decision trees. You'll build the orchestration systems that enable these agents to surface insights that would take analysts hours to find, with full audit trails showing exactly how conclusions were reached.

Within your first 90 days, you will:

1. Design and ship your first multi-agent workflow system into production with senior mentorship
2. Build and deploy an agent orchestration service handling real financial research tasks
3. See your code power autonomous research workflows at top financial institutions
4. Take ownership of a core agent system from architecture to production deployment

What You'll Build

Agent Orchestration & Workflow Engineering

You'll design and implement sophisticated agent coordination systems that manage complex, multi-step research workflows. You'll build state machines, task queues, and execution engines that coordinate specialized AI agents across diverse data sources and analysis tasks.

Multi-Agent System Architecture

You'll architect scalable systems for agent communication, task delegation, and result synthesis. You'll implement patterns for agent specialization, load balancing, and dynamic resource allocation across research workflows.

Autonomous Task Execution

You'll build robust execution frameworks that handle long-running, multi-phase research tasks with automatic retry logic, error recovery, and graceful degradation. You'll ensure agents can autonomously navigate complex decision trees while maintaining human oversight capabilities.

AI Model Integration & Management

You'll integrate and orchestrate multiple language models (GPT, Claude, specialized financial models) with intelligent routing, fallback mechanisms, and cost optimization. You'll build abstraction layers that allow seamless model swapping and A/B testing.

Real-Time Data Pipeline Architecture

You'll design high-throughput data ingestion systems that process streaming financial data, SEC filings, news feeds, and alternative datasets. You'll build event-driven architectures that trigger agent workflows based on real-time market events.

What You Bring

Must-Have Qualifications

1. 5+ years of backend systems experience building production-scale distributed systems
2. Strong CS fundamentals: distributed systems, algorithms, system design, and debugging complex multi-service architectures
3. Experience with agent frameworks or multi-agent system design patterns
4. Expert-level proficiency in Python, Node.js, or Rust with experience in microservices and event-driven architectures
5. Hands-on experience with vector databases (Pinecone, Weaviate, Chroma) and semantic search systems
6. Track record of shipping production systems that handle mission-critical workloads
7. Clear technical communication skills for collaborating with both technical and business stakeholders

Nice-to-Haves

1. Experience building AI/ML production systems, workflow orchestration, or autonomous agent platforms
2. Background with financial data, APIs, or enterprise integration (Bloomberg Terminal, trading systems)
3. Knowledge of message brokers (Kafka), container orchestration (Kubernetes), infrastructure as code
4. Technical leadership experience or startup background building systems from scratch

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

Mentorship & Growth

You'll be directly mentored by engineers who built Palantir's core systems. Expect:

1. Weekly 1:1s with senior engineers who've architected enterprise-scale distributed systems
2. Deep architectural reviews and guidance on agent system design
3. Clear growth path toward technical leadership and system ownership
4. Learning by building—your code will power real financial research from day one

Our Technical Stack

1. Backend: Python, Node.js, Rust, PostgreSQL, Redis
2. AI/ML: OpenAI/Anthropic/OpenRouter, Vector Databases
3. Infrastructure: AWS, Docker, Temporal, Kubernetes, Kafka, Apache Airflow
4. Monitoring: Datadog
5. Tools: Git, GitHub Actions, Pulumi

What We Offer

1. Comprehensive medical, dental, vision, 401k for employees and dependents
2. Latest MacBook Pro, multiple monitors, and ergonomic setup
3. "Build anything" budget for tools, libraries, and infrastructure
4. Learning budget for conferences and courses
5. Daily lunch in office + unlimited PTO

How We Work

1. Forward-Deployed with Product DNA: We own customer outcomes while building a product company
2. Extreme Ownership: Authority comes from initiative, not job titles
3. Production-First Engineering: Design for critical workloads with resilient, observable systems
4. Trust as the Default: Show your work, keep promises, and flag risks early
5. Keep Raising the Bar: Continuous learning is part of the job

Ready to Architect Foundational Agentic Infrastructure?

If you're driven to solve high-stakes engineering problems at the intersection of AI and finance, with mentorship from world-class systems engineers, we need to speak with you.

Apply now and tell us about the most complex distributed system you've built and operated.