AI Senior Engineer (Vision)

Stack

Responsibilities

• ▹Build pipelines that read complex documents, understanding layout, charts and visual context with Vision-Language Models (GPT-4V, Claude 3.5) and layout analysis
• ▹Own the application logic layer: use LangChain or LangGraph to build agents and chains that query data, reason about it and generate responses
• ▹Handle native PDF processing (PyMuPDF, layout parsing) to preserve structure before the AI sees it
• ▹Craft complex prompts and control flows so models interpret financial charts and layouts accurately without hallucinating
• ▹Apply a cost-optimization mindset (batch processing, model selection) so the vision and orchestration layers are economically viable

Requirements

• ▹LLM orchestration (must have): deep experience with LangChain, LangGraph or similar frameworks, including managing context windows, tool calling and agentic workflows
• ▹Multimodal AI experience: hands-on integration of state-of-the-art vision models (GPT-4V, Claude 3.5 Sonnet) and embedding models (CLIP)
• ▹Document intelligence: familiarity with specialized models (e.g., Donut, Pix2Struct) and tools like Unstructured.io or Docling
• ▹PDF processing mastery with tools like PyMuPDF or pdfplumber for native element extraction
• ▹Python ML stack: strong proficiency in PyTorch or TensorFlow
• ▹Strong verbal and written communication skills in English

Nice to have

• ▹Experience fine-tuning vision or language models to improve accuracy on domain-specific artifacts like financial charts or tables
• ▹Prior experience handling documents in the Real Estate or Finance sectors

Soft skills

What we offer

• ▹40 hours per week, available during normal business hours as needed
• ▹Payments made in USD
• ▹18 days of PTO per year, observance of local holidays and an annual break between Christmas and New Year
• ▹Monthly wellness stipend and snack boxes delivered to your home
• ▹AI training, knowledge-sharing and hands-on experimentation

About the company

Able started in 2012 as an engineering and product hub building for a portfolio of early-stage startups. Today it is entering a chapter defined by applied AI and becoming an AI-native organization.