You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
BuzzClan LLC

Sr. AI Engineer

  • Office
  • 6+ years

Salary

Not stated

Similar roles pay $190K - 265K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

Senior AI Engineer role on the Firm Risk Management (FRM) Technology team, focused on agentic AI applications built in Python and LangGraph.

Location is New York City, NY, and the company needs a local candidate who can work in person.

This is a contract position.

Potential use cases include cross-risk variance analysis, credit risk lifecycle workflows, continuous news monitoring, and model risk lifecycle processes.

The work is hands-on software engineering in a governed enterprise environment, with focus on context quality, agent memory, evaluation, observability, and reliable operation.

The role owns technical design and implementation end to end.

Responsibilities

  • Design and build modular, maintainable Python applications, APIs, and services that connect LLMs, enterprise data, and business tools.
  • Build LangGraph agent workflows with explicit state, conditional routing, tool execution, checkpointing, and human approval or escalation where needed.
  • Assemble the context agents receive, including instructions, retrieved information, tool outputs, and conversation history, while staying within token and access-control limits.
  • Write, version, and test prompts, covering structured outputs, grounding instructions, and handling of incomplete or conflicting information.
  • Set up short- and long-term agent memory, including persistence, retrieval, summarization, retention, and isolation between users and sessions.
  • Create evaluation frameworks using representative datasets, repeatable regression tests, and automated and human review that measure answer quality, grounding, tool-call correctness, task completion, and failure behavior.
  • Add observability to LLM and agent systems with Galileo or a comparable platform, tracking traces, quality signals, latency, token usage, cost, and failures.
  • Put guardrails in place against prompt injection, unsafe tool use, sensitive-data exposure, and unsupported outputs, with access controls and auditable execution paths.
  • Work with risk specialists, product owners, data engineers, and platform teams to turn requirements into tested applications and support deployment and troubleshooting.
  • Take part in technical design reviews, code reviews, documentation, and engineering guidance, while continuing to write code.

Requirements

  • Strong hands-on Python engineering: application design, asynchronous programming, APIs, automated testing, error handling, and maintainable code.
  • Proven experience building LangGraph agents with stateful orchestration and integration with external tools or services. Chatbots, tutorials, and concept-only designs do not count.
  • Working knowledge of LLMs, embeddings, retrieval-augmented generation (RAG), vector search, and the tradeoffs in retrieval and context assembly.
  • Hands-on work with context engineering, prompt engineering, and agent memory management.
  • Experience designing evaluation frameworks for LLM or agent applications, including building test sets and interpreting results.
  • Experience with Galileo or a comparable LLM/agent evaluation and observability platform, including tracing failures and using the findings to improve applications.
  • Experience delivering and supporting production applications, with a solid grasp of security, reliability, version control, CI/CD, and production troubleshooting.
  • Ability to explain technical decisions, separate your own contributions from team results, and work well with business and engineering stakeholders.
  • Highly desirable: knowledge of Model Risk Management, model development and validation lifecycles, model documentation, governance, or model monitoring.
  • Highly desirable: experience in broader risk management, especially credit risk, market risk, or financial-services risk workflows.
  • Highly desirable: experience with Snowflake, Databricks, lakehouse architectures, enterprise data pipelines, or governed knowledge integration.
  • Highly desirable: familiarity with Model Context Protocol (MCP), cloud deployment, containers, and enterprise identity and access controls.
  • Highly desirable: prior use of AI coding assistants such as GitHub Copilot, Claude Code, or Amp, with disciplined review, testing, and secure handling of code and data.

Conditions

Based in New York City, NY, with in-person work required.

Contract role.

All candidate information is kept confidential in line with EEO guidelines.

Where you’d work

From the office

About the company

BuzzClan LLC

Office in New York, United States

Your chances

Worth a look before you spend an evening tailoring a CV for it.

  • 19 checks run
  • 1 red flag

Still hiring?

13 checks

1 red flag

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details11 facts · Role, Location, Compensation, Employment
Tech stack
  • Python
  • SQL
  • CI/CD
  • LLMs
  • RAG
  • LangChain
  • Vector databases
  • Databricks
  • Snowflake
Seniority
Senior
Type
Contract
Specialty
ML
Region
United States
Pay period
Annual
Show 5 more factsShow less

Role

Category
Data & Analytics
Specialty
ML
Seniority
Senior
Experience
6+ years
Tech stack
  • Python
  • SQL
  • CI/CD
  • LLMs
  • RAG
  • LangChain
  • Vector databases
  • Databricks
  • Snowflake

Location

Work model
Office
Region
United States
Office
  • New York, United States

Compensation

Salary
Salary by agreement
Pay period
Annual

Employment

Type
Contract

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason