Sr. AI Engineer

BuzzClan LLC•New York, NY
•Onsite

About The Position

The Senior AI Engineer will design, develop, and operationalize agentic AI applications for Firm Risk Management. Potential applications include cross-risk variance analysis, credit risk lifecycle workflows, continuous news monitoring, and model risk lifecycle processes. This is a hands-on software engineering role focused on Python development and building AI agents with LangGraph. The engineer will own technical design and implementation, emphasizing context quality, agent memory, evaluation, observability, and reliable operation in a governed enterprise environment. The role is based in New York City and requires a local resource able to attend in person. It is a contract position on the Firm Risk Management (FRM) Technology team.

Requirements

  • Strong hands-on Python software engineering, including application design, asynchronous programming, APIs, automated testing, error handling, and maintainable code.
  • Demonstrated experience implementing AI agents with LangGraph, including stateful orchestration and integration with external tools or services.
  • Practical understanding of LLMs, embeddings, retrieval-augmented generation (RAG), vector search, and retrieval and context-assembly tradeoffs.
  • Hands-on experience with context engineering, prompt engineering, and agent memory management.
  • Experience designing and implementing evaluation frameworks for LLM or agent applications, including test-set construction and interpretation of evaluation results.
  • Experience with Galileo or a comparable LLM/agent evaluation and observability platform, including tracing failures and using findings to improve applications.
  • Experience delivering and supporting deployed applications, with understanding of security, reliability, version control, CI/CD, and production troubleshooting.
  • Ability to explain technical decisions, distinguish personal contributions from team outcomes, and collaborate effectively with business and engineering stakeholders.
  • Must be local to New York City and able to attend in person.

Nice To Haves

  • Knowledge of Model Risk Management, model development and validation lifecycles, model documentation, governance, or model monitoring.
  • Experience in broader risk management, particularly credit risk, market risk, or financial-services risk workflows.
  • Experience with Snowflake, Databricks, lakehouse architectures, enterprise data pipelines, or governed knowledge integration.
  • Familiarity with Model Context Protocol (MCP), cloud deployment, containers, and enterprise identity/access controls.
  • Prior experience using AI coding assistants such as GitHub Copilot, Claude Code, or Amp, with disciplined review, testing, and secure handling of code and data.
  • Risk management knowledge is highly desirable.

Responsibilities

  • Design and build modular, maintainable Python applications, APIs, and services integrating LLMs, enterprise data, and business tools.
  • Develop LangGraph agent workflows using explicit state, conditional routing, tool execution, checkpointing, and human-in-the-loop approval or escalation where appropriate.
  • Select and assemble relevant instructions, retrieved information, tool outputs, and conversation history for agent context, while respecting token and access-control constraints.
  • Design, version, and test prompts, including structured outputs, grounding instructions, and safe handling of incomplete or conflicting information.
  • Implement short- and long-term memory strategies, including persistence, retrieval, summarization, retention, and isolation between users and sessions.
  • Build evaluation frameworks using representative datasets, repeatable regression tests, and automated and human evaluation; assess answer quality, grounding, tool-call correctness, task completion, and failure behavior.
  • Implement LLM and agent observability using Galileo or comparable platforms, including execution traces, quality signals, latency, token usage, cost, and failure analysis.
  • Apply guardrails for prompt injection, unsafe tool use, sensitive-data exposure, and unsupported outputs; incorporate access controls and auditable execution paths.
  • Collaborate with risk specialists, product owners, data engineers, and platform teams to translate requirements into tested applications and support deployment and troubleshooting.
  • Contribute to technical design reviews, code reviews, documentation, and engineering guidance while remaining actively involved in coding.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service