Senior Software Engineer

Founded in 2014 in Brooklyn, NY, Underdog.io is a modern recruiting platform. One of our seed-funded hiring partners is looking to hire a Sr Software Engineer to join their team in Downtown Brooklyn. They've recently raised a $85M Series A and work with some of the largest hardware companies in the world.

Senior Software Engineer - AI Agent Infrastructure

Location: On-Site | Team: Founding Engineers from Palantir

Architect the Future of Autonomous Research

You have a unique opportunity to build the core intelligent infrastructure for a platform that is transforming how enterprises conduct deep research. Founded by two Palantir veterans who built core components of Gotham and Foundry, we are backed by the founders of OpenAI, Facebook AI, and other iconic tech companies.

Our mission is to replace thousands of hours of manual data gathering with autonomous, transparent, and interactive AI agents. We're starting by tackling a massive problem in financial services, where professionals spend 60-70% of their time collecting data instead of analyzing it. You will build the backend systems that power AI agents to autonomously ingest dozens of data sources, conduct deep analysis, and create interactive decision trees for analysts at top financial institutions.

Within your first 90 days, you will design, ship, and take ownership of a multi-agent workflow system that handles real, mission-critical financial research tasks.

What You’ll Do

You will be foundational in architecting and building the robust, scalable systems that coordinate our autonomous AI agents. Your work will sit at the intersection of AI, distributed systems, and enterprise-grade reliability.

• You will design and implement sophisticated agent orchestration systems, building state machines, task queues, and execution engines that coordinate multiple specialized AI agents across complex, multi-step research workflows.
• You will architect scalable multi-agent systems for communication, task delegation, and result synthesis, implementing patterns for load balancing and dynamic resource allocation.
• You will build robust autonomous task execution frameworks with automatic retry, error recovery, and graceful degradation, ensuring agents can navigate complex decisions while maintaining human oversight.
• You will integrate and manage multiple AI models (GPT, Claude, etc.) with intelligent routing, fallback mechanisms, and cost optimization.
• You will design high-throughput data pipelines to process streaming financial data, SEC filings, and alternative datasets, building event-driven architectures that trigger agent workflows.
• You will implement sophisticated agent memory and context management systems using vector databases and knowledge graphs to support long-running research sessions.
• You will ensure enterprise-grade reliability, building systems with comprehensive monitoring, audit logging, and security to meet the standards of top financial institutions.

What We're Looking For

Must-Haves:

• You have 5 years of backend systems experience with a proven track record of building production-scale distributed systems.
• You possess strong CS fundamentals in distributed systems, algorithms, and complex system design.
• You have experience with agent frameworks or multi-agent system design patterns.
• You have expert-level proficiency in Python, Node.js, or Rust and experience with microservices and event-driven architectures.
• You have hands-on experience with vector databases (Pinecone, Weaviate, Chroma) and semantic search.
• You have a clear track record of shipping mission-critical systems that handle real user traffic.
• You communicate complex technical concepts clearly to both technical and business stakeholders.

Nice-to-Haves:

• Experience building AI/ML production systems, workflow orchestration, or autonomous agent platforms.
• Background with financial data or enterprise integration (e.g., Bloomberg Terminal, trading systems).
• Knowledge of advanced tech: Kafka, Kubernetes, infrastructure as code.
• Technical leadership experience or a history of building systems from scratch in a startup or side projects.

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

Mentorship & Growth

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

• Weekly 1:1s with senior engineers who have architected enterprise-scale distributed systems.
• Deep architectural reviews and guidance on agent system design.
• A clear growth path toward technical leadership and system ownership.
• The opportunity to learn by building—your code will power real financial research from day one.

Our Technical Stack

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

What We Offer

• Comprehensive Benefits: Medical, dental, vision, 401k, and insurance for employees and dependents.
• Top-Tech Setup: Latest MacBook Pro, multiple monitors, and an ergonomic setup.
• "Build Anything" Budget: Dedicated funding for any tools, libraries, or infrastructure you need to solve challenges.
• Learning Budget: Attend any conference or course that makes you better.
• Daily Lunch provided in the office.
• Unlimited PTO.

Our Operating Principles

• Forward-Deployed with Product DNA: We own customer outcomes. We don't win if our customers don't win.
• Extreme Ownership: You have the initiative, you have the accountability. Authority comes from action.
• Production-First Engineering: We design for critical workloads from day one with resilient, observable systems.
• Trust as the Default: We show our work, keep our promises, and flag risks early.
• Keep Raising the Bar: Continuous learning isn't a perk; it's part of the job.

Ready to Build Foundational Agentic Infrastructure?

If you are a systems thinker driven to solve high-stakes engineering problems and want to be mentored by the best, we need to speak with you. Apply now and tell us about a complex distributed system you've built.