Sr. AI Engineer

BuzzClan LLC

  • New York, NY
  • On-site
  • Senior level
  • AI/ML Engineering
  • Visa: not specified

The role in 30 seconds

BuzzClan LLC is seeking a hands-on Senior AI Engineer to design, develop, and operationalize agentic AI applications for Firm Risk Management. The role focuses on building LangGraph-based agent workflows, context and prompt engineering, agent memory, evaluation, and observability in a governed enterprise environment. The engineer will collaborate with risk specialists and data teams to deliver reliable, secure AI solutions for risk management use cases.

Is this role a fit for you?

The backgrounds this role is most likely to hire from, as RoleStack reads the posting.

Strong match

  • B2B enterprise platform / workflow software
  • Data platform / ML pipeline
  • B2B infrastructure / API / developer tools
  • Enterprise-scale
  • Regulated environment

Workable stretch

  • Internal tooling / back-office systems
  • Marketplace / multi-sided platform
  • Growth-stage

Harder transition

  • B2C consumer-facing application
  • Embedded systems / hardware-adjacent
  • Startup / greenfield

Industry: Financial Services & FinTech (risk management). See your personal match score

What they're really screening for

Must-haves

  • CORE Strong hands-on Python software engineering, including application design, asynchronous programming, APIs, automated testing, error handling, and maintainable code
  • CORE Demonstrated experience implementing AI agents with LangGraph, including stateful orchestration and integration with external tools or services—not only chatbots, framework tutorials, or conceptual designs
  • CORE Practical understanding of LLMs, embeddings, retrieval-augmented generation (RAG), vector search, and the tradeoffs involved in retrieval and context assembly
  • CORE Hands-on experience with context engineering, prompt engineering, and agent memory management
  • CORE Experience designing and implementing evaluation frameworks for LLM or agent applications, including test-set construction and interpretation of evaluation results
  • CORE Experience with Galileo or a comparable LLM/agent evaluation and observability platform, with the ability to trace failures and use findings to improve applications
  • PLUS Experience delivering and supporting deployed applications, with sound understanding of security, reliability, version control, CI/CD, and production troubleshooting
  • PLUS Ability to explain technical decisions, distinguish personal contributions from team outcomes, and collaborate effectively with business and engineering stakeholders
  • CORE Experience building for risk management or financial risk workflows (inferred from responsibilities and domain context)

Nice-to-haves

  • PLUS Knowledge of Model Risk Management, model development/validation lifecycles, model documentation, governance, or model monitoring
  • PLUS Experience in broader risk management, particularly credit risk, market risk, or financial-services risk workflows
  • PLUS Experience with Snowflake, Databricks, lakehouse architectures, enterprise data pipelines, or governed knowledge integration
  • PLUS Familiarity with Model Context Protocol (MCP), cloud deployment, containers, and enterprise identity/access controls
  • PLUS 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

Résumé keywords for this role

Terms the posting stresses. Include the ones you can honestly back up.

Tools & technologies

  • Python
  • LangGraph
  • LLMs
  • RAG
  • Galileo
  • Snowflake
  • Databricks
  • lakehouse
  • MCP
  • GitHub Copilot
  • Claude Code
  • Amp
  • CI/CD
  • APIs
  • asynchronous programming

Concepts & phrases

  • Senior AI Engineer
  • Agentic AI
  • Firm Risk Management
  • LangGraph-based agent workflows
  • context engineering
  • prompt engineering
  • agent memory management
  • evaluation frameworks
  • LLM observability
  • retrieval-augmented generation
  • vector search
  • human-in-the-loop
  • model risk management
  • credit risk
  • market risk

Words that count as the same thing: "LangGraph" ≈ LangChain agent framework, Agentic workflow orchestration · "RAG" ≈ Retrieval-Augmented Generation, Retrieval-augmented generation · "LLM" ≈ Large Language Model, Large Language Models · "CI/CD" ≈ Continuous Integration/Continuous Deployment, Continuous Integration and Continuous Delivery · "Model Risk Management" ≈ MRM, Model Risk Governance

Check my résumé against these keywords

Hiring at BuzzClan LLC

Open senior roles RoleStack tracks right now, posted in the last 30 days.

More open roles at BuzzClan LLC

Full job description from BuzzClan LLC

From BuzzClan LLC's posting. View the original

Senior AI Engineer (Agentic AI, Python & Risk Management)

Location: New York City, NY (Need local resource who can go for In-person)

Contract

Team: Firm Risk Management (FRM) Technology

Additional Points: Strong Python and hands-on LangGraph experience, including context/prompt engineering, memory, evaluation, and observability using Galileo or similar tools. Risk management knowledge is highly desirable. Strong Python, SQL, and data engineering skills, with practical understanding of AI agents, context/prompt engineering, memory, evaluation, and observability.

Show full description Show less

About the role

We are seeking a hands-on Senior AI Engineer to design, develop, and operationalize agentic AI applications for Firm Risk Management. Potential use cases include cross-risk variance analysis, credit risk lifecycle workflows, continuous news monitoring, and model risk lifecycle processes. This is a software engineering role requiring strong Python design and development skills and practical experience building AI agents with LangGraph. The successful candidate will own technical design and implementation, with particular focus on context quality, agent memory, evaluation, observability, and reliable operation in a governed enterprise environment.

Key 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.
• Build evaluation frameworks with representative datasets, repeatable regression tests, and appropriate 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 technical design reviews, code reviews, documentation, and engineering guidance while remaining actively involved in coding.

Required skills and experience

• 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—not only chatbots, framework tutorials, or conceptual designs.
• Practical understanding of LLMs, embeddings, retrieval-augmented generation (RAG), vector search, and the tradeoffs involved in retrieval and context assembly.
• 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, with the ability to trace failures and use findings to improve applications.
• Experience delivering and supporting deployed applications, with sound 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.
Highly desirable

• Knowledge of Model Risk Management, model development/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.

All your information will be kept confidential according to EEO guidelines.

FAQ

Does BuzzClan LLC sponsor visas for this role?

The posting does not say whether visa sponsorship is available. Ask the recruiter before you apply.

Is this role remote?

It is an on-site role.

What tools and technologies does the posting mention?

Python, LangGraph, LLMs, RAG, Galileo, Snowflake, Databricks, lakehouse, MCP, GitHub Copilot, Claude Code, Amp, CI/CD, APIs, asynchronous programming.