Senior AI Software Engineer – AI Labs
Contractor | Remote | Latam
About the Company
Our client is a leading visual outfitting and styling solution for the world's top retailers and brands, serving approximately 100 million shoppers monthly. Their clients include globally recognized names in fashion, sportswear, and home goods. Founded in 2011, they use a powerful combination of algorithms, trend data, and stylist expertise to deliver millions of on-brand outfit recommendations daily across e-commerce, email, advertising, stores, and social media.
About the Client's AI Labs Division
The client's AI Labs division was launched in 2026 to work directly with senior leaders at enterprise retailers and brands on AI initiatives that sit outside traditional product roadmaps. They partner by invitation with a small number of retailers at a time, focusing on problems that require real domain expertise and that horizontal LLMs cannot solve on their own.
The client's AI Labs delivers production-ready systems in 90-day sprints, structured across three phases: Domain Discovery, Model Training & Tuning, and Production Deployment. Current production initiatives include Advanced Personalization, Virtual Try-On, and Analytics.
About the Role
We are looking for an experienced AI Software Engineer to join AI Labs and help shape the future of how AI models are empowered with the data, tools, and expertise they are missing out of the box. In this role, you'll combine your expertise in software engineering, product sensitivity, and prompt design to drive innovation in AI model-based applications across various retail use cases and multiple clients.
This is a full-stack role. Front-end skills matter because so much of what Labs does is prototyping — you need to be able to stand up a UI that shows stakeholders what something can do. Back-end skills matter because we care about databases, application architecture, and building systems that scale across multiple clients. You'll work fairly independently while connecting with cross-functional teams to prototype, test, and deploy unique solutions. This is a hands-on individual contributor role reporting directly to the CTO, with high visibility and the opportunity to influence the way we build, monitor, and evaluate next-generation AI systems. If you're excited about exploring the frontiers of generative AI and making a direct impact through production-level contributions, we'd love to meet you.
What You Will Do
- Write production-level code in TypeScript (with AI tools)
- Build full-stack prototypes, including front-end interfaces that demonstrate capability to stakeholders and clients
- Prompt engineering and testing with LLMs, including Claude, Gemini, and OpenAI models
- Context engineering to determine the right data to surface to LLMs and agents
- Agentic workflow design
- Help build systems to easily monitor and test LLM performance
- Analyze large data sets
- Design and implement solutions for scale and maintainability across multiple clients
- Contribute as a thought leader to conversations around LLM usage, including challenging or proposing technical directions and identifying what to worry about (and what not to) early in a project
Must-Have Qualifications
- Bachelor's Degree in Computer Science, Data Science, Statistics, or related fields — or equivalent experience
- 7+ years of software development experience, including work within retail, e-commerce, or another applied AI/technology industry
- Confident communication skills (written and oral) with demonstrated ability to work collaboratively across all levels. Strong asynchronous written communication in English is essential — the team works across time zones with small, distributed teams
- Strong problem-solving, attention to detail, organizational, and time management skills, along with demonstrated strategic thinking
- Working experience with modern prototyping stacks: React, TypeScript, and SQL
- Experience with LLMs, testing, and prompt engineering, including work with Claude, Gemini, and OpenAI APIs
- Demonstrated affinity for and experience with agentic software engineering — either on the job or on your own time
- Solid understanding of system design, scalability principles, APIs, and open-source packages
- Demonstrated ability to evaluate model performance using structured test cases and metrics
- Ability to operate independently with ambiguity in product definition
- Judgment to know when to trust an LLM's output and when to challenge it — grounded in actual engineering knowledge and experience
Nice-to-Have Qualifications
- Experience at a high-growth startup, comfortable with the unknown
- Working experience building test workflows for LLMs
- Familiarity with additional programming languages such as Java or Python for data processing or AI prototyping