Senior Software Engineer – AI Tools | Data Engineering | Experienced Hire

Susquehanna International Group, LLPNew York, NY
1dOnsite

About The Position

Susquehanna is hiring a Senior Software Engineer to design and build production-grade AI agents that reduce operational overhead for developers, quants, and traders. This role sits at the intersection of AI systems engineering and workflow automation, focused on developing autonomous and semi-autonomous tools that streamline triage, improve knowledge sharing, and enhance internal productivity. This is a hands-on role within a newly formed initiative. You will independently architect and deploy agentic systems that interact with codebases, APIs, internal tools, and data pipelines. The goal is to build reliable, high-signal AI systems that operate safely, securely, and at scale.

Requirements

  • 5–10+ years of software engineering experience.
  • Proven track record building AI-powered applications, automation platforms, or agentic systems in production environments.
  • Demonstrated ability to design systems that operate with minimal human intervention.
  • Expert-level Python (async, typing, packaging, testing best practices).
  • Experience building AI agents that interact with APIs, tools, codebases, and shell environments.
  • Strong understanding of RAG patterns and vector databases (e.g., Pinecone, Chroma, pgvector).
  • Familiarity with agent frameworks (LangChain, LangGraph, or similar).
  • Deep understanding of LLM behavior, constraints, and mitigation strategies.
  • Strong system design skills with the ability to work independently in a fast-evolving space.
  • Experience handling sensitive or proprietary data securely.

Responsibilities

  • Design and implement autonomous AI agents that execute multi-step workflows across internal systems.
  • Build and productionize retrieval-augmented generation (RAG) architectures using structured, permissioned data sources.
  • Develop agent memory, orchestration layers, and inter-agent communication patterns.
  • Define tool schemas and translate ambiguous stakeholder needs into deterministic agent behaviors.
  • Implement safeguards to mitigate LLM failure modes (hallucination, prompt drift, context management, rate limits).
  • Partner directly with developers, quants, and traders to identify automation opportunities and deploy solutions.
  • Evaluate and integrate emerging models, frameworks, and open-source AI tooling.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service