Senior AI Engineer: Multimodal & LLM Orchestration (Remote)

Embedded Shishya; United States; Remote; USD 120,000 - 190,000; Full time

Benefits offered by this job

Remote work within LatAm

Wellness stipend

AI Voucher

18 days PTO

Job summary

Able is seeking an engineer who thrives at the intersection of computer vision and logic, responsible for extracting data from visual documents and guiding how that data is used by large language models. You’ll be the eyes and brain of our system, building data pipelines that read complex documents, understand layouts, charts, and visual context using GPT-4V and related models.

The role emphasizes building vision-language workflows, managing LangChain/LangGraph, native PDF handling, and prompt

Qualifications

• Experience with LangChain/LangGraph and managing tool calls.
• Hands-on experience with vision models like GPT-4V/Claude 3.5 and embedding models.
• Familiarity with Donut, Pix2Struct, Unstructured.io or Docling.

Responsibilities

• Build pipelines to read complex documents using Vision-Language Models and Layout Analysis.
• Own the application logic layer with agents and chains.
• Handle native PDF processing to preserve structure before AI.
• Craft prompts and control flows to minimize hallucinations.
• Optimize cost and scale for the vision and orchestration layers.

Skills

LangChain

Vision-Language

PDF Processing

PyTorch/TensorFlow

Multimodal AI

Tools

PyMuPDF

pdfplumber

Unstructured.io

Docling

LangGraph

Job description

Able is seeking an engineer who thrives at the intersection of computer vision and logic, responsible for extracting data from visual documents and guiding how that data is used by large language models. You’ll be the eyes and brain of our system, building data pipelines that read complex documents, understand layouts, charts, and visual context using GPT-4V and related models.

The role emphasizes building vision-language workflows, managing LangChain/LangGraph, native PDF handling, and prompt