- New York City, New York, United States
- On-site
- Contract · Senior
Design, develop, and operationalize agentic AI applications for Firm Risk Management using Python and LangGraph.
Responsibilities
- Design and build modular, maintainable Python applications, APIs, and services that integrate LLMs, enterprise data, and business tools.
- Develop LangGraph-based agent workflows with explicit state, conditional routing, tool execution, checkpointing, and human-in-the-loop approval or escalation where appropriate.
- Engineer the context supplied to agents: select and assemble relevant instructions, retrieved information, tool outputs, and conversation history within token and access-control constraints.
- Design, version, and test prompts, including structured outputs, grounding instructions, and safe handling of incomplete or conflicting information.
- Implement appropriate short- and long-term memory strategies, including persistence, retrieval, summarization, retention, and isolation between users and sessions.
Requirements
- Nice to have: Model Risk Management
- Nice to have: Credit risk
- Nice to have: Market risk
- Nice to have: Financial-services risk workflows
- Nice to have: Snowflake
