AI / ML Engineer

Foliox; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Health, dental & vision coverage

Unlimited PTO

Conference & learning budget

Equity offered

Job summary

Foliox is seeking an AI Engineer to develop and deploy AI systems that automate dispatch operations in a remote-first US role. You will work on language-model agents for order intake and triage, document processing, demand forecasting, and pricing intelligence.

Responsibilities include building LLM agents, document extraction for reconciliation, forecasting models, and designing evaluation methods. You will deploy and monitor models in production with feedback loops.

Qualifications

• Three+ years of applied AI or ML in production systems.
• Experience with Python and ML frameworks (PyTorch or TensorFlow).
• Experience with LLMs, RAG pipelines, or agent frameworks.

Responsibilities

• Build and fine-tune LLM-based agents for order intake and dispatch triage.
• Develop document extraction models for bill of lading reconciliation.
• Create demand forecasting models for inventory management.
• Design evaluation methods to measure agent accuracy and reliability.
• Deploy models with production monitoring and feedback loops.

Skills

Python

PyTorch or TensorFlow

LLMs / retrieval-augmented generation

MLOps practices

Model monitoring

Education

Bachelor's or Master's in CS/ML

Tools

PyTorch

TensorFlow

OCR tools

Job description

Role overview

Develop and deploy AI systems that automate parts of dispatch operations. The work spans language-model agents for order intake and triage, document processing, demand forecasting, and pricing intelligence, with responsibility for evaluating and monitoring models in production.

Responsibilities

• Build and fine-tune LLM-based agents for order intake and dispatch triage.
• Develop document extraction models to support bill of lading reconciliation.
• Create demand forecasting models for inventory management.
• Design evaluation methods to measure agent accuracy and reliability.
• Deploy models with production monitoring and feedback loops.

Requirements

• At least three years of applied AI or machine learning experience in production systems.
• Strong Python skills and experience with PyTorch or TensorFlow.
• Experience with LLMs, retrieval-augmented generation pipelines, or agent frameworks.
• Understanding of MLOps practices, including model versioning, monitoring, and A/B testing.
• A bachelor’s or master’s degree in computer science, machine learning, or a related field, or equivalent experience.

Nice to have

• Experience with voice AI or speech-to-text systems.
• Background in OCR or document extraction.
• Familiarity with fuel or energy industry data.

Benefits and work setup

• Remote-first role for candidates in the US.
• Health, dental, and vision coverage, unlimited paid time off, and a conference and learning budget.
• Competitive salary and equity are offered.