Job Summary
We’re looking for a versatile AI Developer to join our newly formed AI squad. In this role, you will architect, build, and ship RAG pipelines, conversational AI features, and intelligent knowledge-retrieval systems—all tightly integrated into our TypeScript-based product ecosystem. You’ll partner closely with product and engineering teams to deliver AI-powered experiences that directly impact patient care and clinic operations.
Responsibilities
Design, develop, and deploy RAG-based systems using TypeScript, Node.js, and vector databases.
Build production-grade conversational AI solutions, including chatbots, virtual assistants, and guided workflows, for web and mobile applications.
Develop and maintain REST and GraphQL APIs that expose AI-powered services to internal teams and external consumers.
Integrate cloud AI platforms and orchestration frameworks.
Implement low-latency inference solutions using TensorFlow.js and ONNX.js across client-side and server-side environments.
Collaborate with ML engineers and data scientists to incorporate embeddings, pre-trained models, and fine-tuned LLMs into production applications.
Embed AI capabilities into React/Next.js front ends and Node.js back ends in partnership with product and engineering teams.
Optimize AI features for scalability, performance, cost efficiency, and seamless user experience.
Build reusable components, SDKs, and internal tooling to scale AI adoption across products.
Qualifications and Job Requirements
4+ years of experience in software development using TypeScript and JavaScript.
Strong experience with Node.js, React, and Next.js in production environments.
Solid understanding of NLP, conversational AI, and RAG-based architectures.
Hands-on experience integrating LLMs, embeddings, and AI-powered workflows into production applications.
Experience with REST and GraphQL APIs, including integrations with cloud AI services.
Familiarity with vector databases such as Pinecone, Weaviate, or pgvector.
Experience with LangChain, LlamaIndex, or similar orchestration frameworks.
Hands-on experience with TensorFlow.js, ONNX.js, or comparable inference frameworks.
Proficiency in Python for model training, preprocessing, fine-tuning, or embedding workflows.
Proven ability to deliver scalable, high-quality software in cross-functional, remote-first environments
What We Offer
100% Remote Work: Enjoy the freedom to work from the location that helps you thrive. All it takes is a laptop and a reliable internet connection.
Highly Competitive USD Pay: Earn an excellent, market-leading compensation in USD, that goes beyond typical market offerings.
Paid Time Off: We value your well-being. Our paid time off policies ensure you have the chance to unwind and recharge when needed.
Work with Autonomy: Enjoy the freedom to manage your time as long as the work gets done. Focus on results, not the clock.
Work with Top American Companies: Grow your expertise working on innovative, high-impact projects with Industry-Leading U.S. Companies.
Why You’ll Like Working Here
A Culture That Values You: We prioritize well-being and work-life balance, offering engagement activities and fostering dynamic teams to ensure you thrive both personally and professionally.
Diverse, Global Network: Connect with over 600 professionals in 25+ countries, expand your network, and collaborate with a multicultural team from Latin America.
Team Up with Skilled Professionals: Join forces with senior talent. All of our team members are seasoned experts, ensuring you're working with the best in your field.