Offer summary

Qualifications:

3+ years of experience with OCR in technical document environments., Proficiency in Python and familiarity with OCR frameworks., Experience in spatial reasoning and text-object matching., Understanding of HVAC domain-specific notations is a plus..

Key responsibilities:

Design an OCR pipeline using frameworks like TrOCR or EasyOCR.

Match detected texts with corresponding visual elements using spatial heuristics.

Clean and normalize extracted metadata for structured data.

Collaborate with backend engineers to integrate structured data into Excel pipelines.

Job description

About Us

We are Vizio.ai, a pioneering data science agency specializing in crafting data visualizations, dynamic dashboards, and innovative data app development. Our mission is to provide cutting-edge solutions and services to a diverse clientele, including top-tier international organizations, large enterprises, SMEs, and forward-thinking agencies, as they embark on transformational journeys.

At VIZIO, we're driven by a singular mission: to empower organizations with high-quality data services and products that unlock the hidden potential within their data. We envision a world where organizations are aware of their today and confident about their future with the power of data.

Our ambition extends beyond the present; we aspire to be leaders in the data industry. We aspire to provide our customers with limitless creative possibilities, reshaping the industry through innovation and inspiring projects. At VIZIO, pioneering the world of data science is our goal, not just for our clients but for our dedicated employees as well.

Join us in shaping the future of data science and inspiring a new era of possibilities.

About The Role

We’re looking for an OCR/NLP-focused engineer to extract structured text from HVAC engineering drawings. Your mission is to accurately extract and associate key metadata like dimensions, CFM values, and air types with corresponding visual elements.

Key Responsibilities

Design an OCR pipeline using TrOCR, EasyOCR, PaddleOCR or similar.

Match detected texts with corresponding detected objects using spatial heuristics.

Clean and normalize extracted metadata (e.g., “32x14” → width=32, height=14).

Collaborate with backend engineers to feed structured data into Excel pipelines.

Requirements

3+ years working with OCR in noisy or technical document environments.

Python proficiency with OCR frameworks and image preprocessing.

Experience in spatial reasoning and text-object matching.

Understanding of domain-specific notations is a plus (e.g., HVAC shorthand).

What We Offer

Innovation in AI & Data: Work on pioneering AI and data projects that shape the future.
Flexibility of Remote Work: Work from anywhere, enjoying the freedom to choose your workspace.
Competitive Rewards: Enjoy a salary that matches your expertise, plus performance bonuses.
Ownership & Growth: Take the lead on projects with the opportunity for significant career advancement.
Structured Career Path: We provide a clear roadmap for your professional development in the tech industry.

Our Core Values

Ownership Mindset: Embrace your role fully, with the initiative to solve problems and the drive to excel.
Continuous Learning: Stay curious, embracing change and challenges as opportunities for growth.
Making Things Happen: Focus on progress and taking decisive steps forward, learning and iterating for excellence.
Thinking Forward: Anticipate the future, plan for long-term success, and make a lasting impact.

How To Apply

If you're ready to take on this challenge and make a significant impact at Vizio AI, we would love to hear from you. Please submit your application, including your resume and a cover letter explaining why you're the perfect fit for this role. Join us in our mission to empower organizations through the power of data.

Vizio AI is an equal-opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

Required profile