At LightBox, we strive to not only equip confident, data-driven decisions across sectors, but to also enrich lives by bringing people, information, and technology together. As a company with a wide range of clients, we believe a diverse workforce is crucial to success. Our commitment to inclusion across race, gender, age, religion, identity, and experience is the foundation upon which we operate and connect with our customers and the communities in which we work.
With our expertise, we are producing the best available data, workflow tools, technology, and analytics to support everyone making a real estate decision. There has never been a better time to make an impact and we invite you to join us on this journey.
LightBox is a leading provider of data and workflow solutions across commercial real estate and location intelligence. Our solutions deliver the depth, speed and accuracy that enable insights to over 50,000 brokers, 1,000 banks and lenders, 1,000 law firms and 5,000 environmental consulting and engineering firms.
ML Engineer
About the Role
We’re seeking a versatile and passionate full stack, polyglot (python, typescript, golang, etc…) engineer with, preferably, experience related to document intelligence. This role centers around advancing generative AI solutions and designing and building intelligent document extraction pipelines.
You’ll join a fast-moving, versatile, agile team building cutting-edge systems that transform unstructured content into meaningful insights, powering smarter decisions across the commercial real estate industry. You’ll flex your polyglot engineering muscles while working alongside researchers and product teams in a dynamic, startup-like environment with the backing of a larger company.

Key Responsibilities

• Design and develop systems using Python, Golang, and TypeScript
• Build and optimize workflows, LLM pipelines, and custom inference services for document understanding
• Design and deploy microservices and APIs for AI-based content creation and extraction
• Apply statistical and machine learning techniques to improve data accuracy and streamlining existing workflows
• Collaborate with product teams, data team
• Own end-to-end delivery of features—from ideation to deployment and monitoring
• Conduct code reviews and mentor junior developers

Required Skills

• 3-5+ years of software development experience across Python, TypeScript, SQL, and Golang
• Familiarity with geospatial analysis tools and techniques and commercial real estate is highly desirable
• Hands-on experience with LLMs and generative AI frameworks (e.g. AWS Bedrock, OpenAI, etc…)
• Experience developing document ingestion and extraction systems (PDFs, forms, receipts, contracts, appraisals, etc…)
• Good working knowledge around cloud native architecture (preferably AWS, specifically EKS, MSK, OpenSearch, etc… )
• Proficient with CI/CD workflows and containerization (Docker, Kubernetes, ArgoCD, GitHub Actions)
• Strong understanding of modern software engineering practices and SDLC

Nice to Have

• Exposure to Retrieval-Augmented Generation (RAG) techniques
• Experience with vector databases
• Familiarity with TypeScript React or frontend visualization tools

What We Offer

• Opportunity to shape frontier ML/AI technologies and use cases in the company
• A high-ownership environment with room to grow and experiment
• Flexible work hours and hybrid/remote-friendly culture

We thank all applicants in advance for their interest in this position, however, only those selected for an interview will be contacted.
This job description is a general listing of the required tasks and expectations of the position and in no way implies that the duties listed above are the employee’s only responsibilities. The employee is expected to perform other tasks, responsibilities and training as instructed by their supervisors. Duties and responsibilities may change at any time with or without notice.
This position may require additional hours outside of the standard work schedule including occasional holiday, evening and/or weekend hours in order to meet deadlines or to accommodate customers.
LightBox and all its holding companies are an equal opportunity/affirmative action employer. It is the policy of the LightBox and its holding companies to prohibit discrimination of any type and to afford equal employment opportunities to employees and applicants, without regard to race, color, religion, sex, national origin, age, disability, or veteran status.

• Design and develop systems using Python, Golang, and TypeScript
• Build and optimize workflows, LLM pipelines, and custom inference services for document understanding
• Design and deploy microservices and APIs for AI-based content creation and extraction
• Apply statistical and machine learning techniques to improve data accuracy and streamlining existing workflows
• Collaborate with product teams, data team
• Own end-to-end delivery of features—from ideation to deployment and monitoring
• Conduct code reviews and mentor junior developer