AI ML Automation Engineer Intern: Build LLM Workflows & Pipelines

Akoncagua AI; Lakeland (FL); On-site; USD 28,000 - 41,000; Part time

Job summary

Akoncagua AI is seeking an AI Automation Engineer Intern to help design and deploy secure AI agents and automated workflows for accounting and enterprise finance. The role focuses on building LLM-based agent systems, document-intelligence pipelines, and end-to-end evaluation frameworks in a collaborative research environment.

You will work on integrating agents with accounting platforms, databases, and internal APIs, while developing robust tracing, observability, and cost controls for

Qualifications

• Currently enrolled in a Master's or PhD program in Computer Science, AI/ML, or a related technical field, or equivalent practical experience.

Responsibilities

• Build and improve LLM agent workflows for document intake, classification, and transaction coding.
• Develop document-intelligence pipelines for invoices, receipts, contracts, and financial statements.
• Implement retrieval over accounting policies, vendor records, and historical transactions.
• Write evaluation harnesses that measure extraction accuracy, classification quality, and end-to-end workflow outcomes.
• Add tracing and observability for prompts, tool calls, failures, latency, and cost.
• Integrate agents with accounting platforms, databases, and internal APIs.

Skills

Python

Data structures

Debugging

Testing

LLM apps

LangGraph

AutoGen

Semantic Kernel

OpenAI Agents SDK

RAG

Vector databases

Docker

Git

Education

Masters/PhD in CS/AI

Tools

LangGraph

AutoGen

Semantic Kernel

OpenAI Agents SDK

Job description

Akoncagua AI is seeking an AI Automation Engineer Intern to help design and deploy secure AI agents and automated workflows for accounting and enterprise finance. The role focuses on building LLM-based agent systems, document-intelligence pipelines, and end-to-end evaluation frameworks in a collaborative research environment.

You will work on integrating agents with accounting platforms, databases, and internal APIs, while developing robust tracing, observability, and cost controls for