AdTechTalent
Data Science4 months agoHybrid

Kargo

AI Engineer

AILLMautomationorchestrationPythonJavaScriptChatGPTSnowflakeSalesforceSlackprompt engineeringagent workflowsdata scienceAI opsinternal toolsSaaS APIsvector databasesRAG pipelines

Key details

Salary

Not specified

Employment type

Full-time

Seniority

Senior

Years experience

5-10

Location

New York, US

Full job description

Kargo is hiring a Senior AI Engineer to architect, build, and scale AI-powered products and automations for the commercial organization. This hybrid role requires onsite presence 4 days per week in New York, NY. The engineer will work within the Data & AI team to identify high-value use cases, build intelligent workflows and agentic applications, and deploy AI systems across Salesforce, Snowflake, Slack, and other platforms. Responsibilities include designing and maintaining AI automations using orchestration frameworks (LangGraph, n8n, OpenAI tooling), translating business pain points into modular automation flows, building production-grade LLM applications with ChatGPT Enterprise, maintaining governance models for prompt engineering and audit trails, and collaborating cross-functionally to drive adoption and own the AI Ops roadmap. Required skills include 5-8+ years in systems automation or process/data engineering, proficiency in Python or JavaScript, experience with orchestration platforms and SaaS APIs, and familiarity with LLM application frameworks. Nice to have experience includes prompt libraries, vector databases, Retool or Streamlit, and Kubernetes CI/CD. Salary range is $140,000 to $180,000 USD.

What you'll do

  • Architect, build, and scale AI-powered products and automations for commercial organization
  • Identify high-value use cases and build intelligent workflows and agentic applications
  • Deploy trustworthy AI systems across Salesforce, Snowflake, Slack, and other internal platforms
  • Design, build, deploy, and maintain AI-powered automations and agent workflows using modern orchestration frameworks
  • Translate business pain points into modular, extensible automation flows that are observable, debuggable, and fault-tolerant
  • Build production-grade LLM applications for knowledge surfacing, workflow routing, decision support, and dynamic content generation
  • Maintain governance model for prompt engineering and audit trails
  • Work cross-functionally to discover automation opportunities, prototype quickly, document tooling, and drive self-service adoption
  • Own and drive AI Ops roadmap prioritized by business impact and feasibility
  • Establish governance model covering prompt engineering standards, audit trails, and feedback loops
  • Serve as internal thought leader on applied AI

Requirements

  • 5–8+ years in systems automation, internal tools, or process/data engineering
  • Hands-on experience with orchestration platforms such as n8n, LangGraph, Zapier, or Make
  • Strong familiarity with SaaS APIs and system interoperability
  • Experience building production-grade LLM applications using ChatGPT Enterprise and related LLM APIs
  • Maintain governance model for prompt engineering, agent testing, and audit trails
  • Familiarity with evaluation and observability frameworks for LLM applications
  • Ability to work cross-functionally with Sales, Client Services, Media Strategy, Marketing, Product, and Ops
  • Own and communicate AI Ops roadmap
  • Experience with prompt libraries, embeddings-based retrieval, or vector databases (Pinecone, Weaviate) and RAG pipelines (nice to have)
  • Experience with Retool or Streamlit for lightweight internal UIs; ArgoCD or Kubernetes CI/CD experience (nice to have)

Tech stack

PythonJavaScriptLangGraphn8nOpenAIChatGPT EnterpriseSnowflakeSalesforceSlackAtlassianGoogle WorkspaceLookerAirtableClaude CodeCursorCodexPineconeWeaviateRetoolStreamlitArgoCDKubernetes

Apply now

Ready to take the next step in your career? Click the button below to continue to the application process.

Similar jobs

More roles worth a look

Related opportunities based on specialty and working model so candidates can keep momentum.