AI Senior Engineer - Vision

AI overview

This role focuses on leveraging cutting-edge AI technologies for computer vision to extract and process complex visual data, enabling high-value insights for various industries.

AI Senior Engineer

 

Our Story

Over the past several years, Able has grown immeasurably. We’ve also grown in the type of company that we are:

 

Chapter 1: We were founded in 2013 as a product and engineering hub for a portfolio of early-stage start-ups. We grew up as an in-house/external hybrid shared services model. That allowed us to hone our skills and establish our operational and cultural foundation.

Chapter 2: In 2019 we began to expand our vision. We began to grow outside of our inset partner base. We had good initial success meeting new partners, kicking off new relationships, and delivering high-value work.

Chapter 3: In 2023, we moved into the next phase of a new chapter, an expansion of the ambition of Chapter 2. Our strategy for growth centers around two audiences:

  • Venture Capital: VC firms are looking for trusted product and technology solutions to distribute seamlessly across their portfolios at scale.
  • Private Equity: PE firms are looking for trusted solutions that can catalyze growth for their portfolio companies at scale.


Chapter 3a: We are now in the next phase of Chapter 3, aligned to our mission and vision, and accelerated by the powers of applied AI. We believe that AI will be a powerful force in the end-to-end software development lifecycle. Specifically we are creating practices that – coupled with our world class talent – can deliver software significantly faster than legacy techniques. The result is increased value for our partners, who can dramatically increase the capacity of their product organizations. 

 

What you’ll be doing

We are seeking someone who enjoys working at the cutting edge where Computer Vision meets Logic. You will be responsible for the "eyes" and the "brain" of our system—extracting complex data from visual documents and then orchestrating how that data is used by Large Language Models.

 

In short, someone who likes:

 

  • Unlocking Visual Data: Building pipelines that can "read" complex documents, understanding layout, charts, and visual context using Vision-Language Models (GPT-4V, Claude 3.5) and Layout Analysis.
  • Orchestrating Intelligence: Owning the application logic layer. You will use LangChain or LangGraph to build the agents and chains that query our data, reason about it, and generate responses.
  • Native PDF Handling: Handling the messy reality of PDF processing (PyMuPDF, layout parsing) to preserve structure before the AI even sees it.
  • Prompt Engineering & Logic: Crafting complex prompts and control flows to ensure models interpret financial charts and layouts accurately without hallucinating.
  • Cost & Scale: Applying a cost-optimization mindset (batch processing, model selection) to ensure our vision and orchestration layers are economically viable.




What we’re looking for

We want to work with people who have a passion for collaborating with their teams, building software while nurturing inclusive and respectful relationships with their coworkers. With the ones that are open about their shortcomings and what they do not know now, but remain eager to keep on growing and closing those gaps.

 

Ideally, they would also have:

  • LLM Orchestration (Must Have): Deep experience with LangChain, LangGraph, or similar frameworks. You know how to manage context windows, tool calling, and agentic workflows.
  • Multimodal AI Experience: Hands-on experience integrating state-of-the-art vision models (GPT-4V, Claude 3.5 Sonnet) and embedding models (CLIP).
  • Document Intelligence Specialist: Familiarity with specialized models (e.g., Donut, Pix2Struct) and tools like Unstructured.io or Docling.
  • PDF Processing Mastery: Mastery over tools like PyMuPDF or pdfplumber for native element extraction.
  • Python ML Stack: Strong proficiency in PyTorch or TensorFlow.

 

Nice-to-Have:

  • Fine-Tuning: Experience fine-tuning vision or language models, specifically to improve accuracy on domain-specific artifacts like financial charts or tables.

Domain Knowledge: Prior experience handling documents in the Real Estate or Finance sectors.

Able's Values

  • Put People First: We're caring, open, and encouraging.  We respect the richness that we each bring into our work.
  • Imagine Better: We are optimistic in our outlook, as well as creative and proactive to deliver the highest quality.
  • Expect Excellence: We commit to each other to always strive to be our best.
  • Simplify to Solve: We create better outcomes by reducing complexity.
  • We are all Builders: We are motivated and empowered to help build Able, and our partner's businesses.
  • One Able. Many Voices: Our unity is our strength.  Our diversity is our energy.

Let’s build together.

Able is a product strategy and development studio. Able's vision is to build digital products that create a more inclusive and prosperous future for our people and partners.  Our teams consist of exceptional Product Designers, Software Engineers, Product Managers, Project Managers, Data Scientists, and all-around company builders. We focus on creating small teams that work closely with partners (our term for “clients”) to start, accelerate, and grow business using technology. Our teams are capable of addressing every stage of the product life cycle including product strategy, research, design, and engineering.

View all jobs
Ace your job interview

Understand the required skills and qualifications, anticipate the questions you may be asked, and study well-prepared answers using our sample responses.

Senior Engineer Q&A's
Report this job
Apply for this job