About WebLife
For over 16 years, WebLife has been a leader in the eCommerce industry, operating category-defining stores and becoming one of the largest distributors of mailboxes in the U.S. Our success comes from building data-driven operations and high-performing teams that thrive in fast-moving markets.
Now, we’re taking that foundation into a bold new venture—building an AI-powered product that will redefine how small and mid-sized businesses operate. Friday Solutions is a new team spun out from WebLife Labs, building tools that make businesses future-ready through AI—turning scattered information into unified organizational intelligence so teams make better decisions faster. FridayOS is the operating system for becoming an AI-ready organization—your documentation becomes living "source code" that powers today's work and tomorrow's autonomous agents.
Backed by the stability and resources of WebLife’s 16-year track record, Friday Solutions moves fast, values technical ownership, and expects every hire to influence product design, architecture, and operational excellence. By combining the agility of a startup with the backing of a proven eCommerce leader, we’re creating an environment where ideas turn into impact—and where you can help write the next chapter of business with AI.
About the Role
We’re hiring an AI Engineer to build production RAG (Retrieval-Augmented Generation) systems and LLM integrations for FridayOS. You’ll develop AI systems that provide intelligent access to business knowledge—building model integrations, inference pipelines, and application interfaces that make our Role Assistants feel like indispensable teammates with persistent organizational memory. You’ll work on a small team of fewer than 10 people, collaborating closely with other AI Engineers on complex, high-impact problems—designing, observing, and refining a cutting-edge product. You’ll report directly to the Product Manager and Solution Architect, partnering with Product, Data, and Delivery teams to ship lovable, reliable AI features on a two-week sprint cadence.
Responsibilities
- Design and implement production RAG systems with vector databases (Qdrant, Pinecone, Chroma, or similar) for organizational knowledge retrieval.
- Build and optimize LLM integrations across multiple providers (OpenAI, Anthropic, or similar) using cost-efficient, reliable production patterns.
- Develop chunking strategies for complex business documents and implement embedding models for semantic search and similarity matching.
- Structure organizational knowledge into a queryable “source code of the business” using vector retrieval with proper permission systems and multi-tenant isolation.
- Create prompt engineering frameworks with systematic optimization, testing, and evaluation for accuracy and relevance.
- Implement context management systems that handle long conversations, organizational memory, and role-aware interactions.
- Build and maintain scalable AI-powered APIs with real-time performance requirements (<2-second response time).
- Establish RAG evaluation systems measuring accuracy, relevance, and hallucination detection with production monitoring and alerting.
- Design multi-provider LLM strategies with graceful fallbacks, rate-limit management, and cost optimization for token usage.
- Develop expertise in agent architecture, making thoughtful decisions about when to use agentic functionality versus simpler approaches—understanding the tradeoffs between autonomy, reliability, and user control.
- Implement authentication, session management, and web security patterns ensuring AI responses respect user access controls.
- Add comprehensive unit and integration test coverage for AI systems with automated quality assurance.
- Collaborate with Data, Product, and Delivery teams to meet sprint gates tied to user experience milestones.
Requirements
Must-Have Qualifications:
- 3+ years of experience building production RAG (Retrieval-Augmented Generation) systems with vector databases and embedding models.
- Advanced Python expertise with AI/ML frameworks (LangChain, Transformers, or similar).
- Production experience with LLM APIs from multiple providers (OpenAI, Anthropic, or similar enterprise integrations).
- Demonstrated expertise in prompt engineering with systematic approaches to optimization, testing, and cost management.
- Experience with vector database integration and similarity search (Qdrant, Pinecone, Chroma, or similar).
- Proficiency in API design for AI systems with real-time performance requirements and scalable concurrent request handling.
- Experience in RAG evaluation including accuracy measurement, relevance scoring, and hallucination detection.
- Knowledge of chunking strategies, embedding optimization, and context construction for business knowledge.
- Experience with multi-tenant AI systems ensuring proper data isolation and permission-aware AI responses.
- Strong understanding of security and privacy principles for enterprise AI systems, including data privacy, compliance, and access controls.
- Experience with production AI monitoring and observability, including performance tracking and alerting.
- Experience working with international teams or clients, preferably in the U.S., U.K., Australia, or Europe.
Preferred Qualifications:
- MLOps experience including model deployment, versioning, and lifecycle management.
- Familiarity with AI evaluation frameworks and systematic quality measurement approaches.
- Experience with model fine-tuning or custom model training.
- Experience with multi-agent orchestration or autonomous agent frameworks.
- Full-stack capabilities including GraphQL, React Query, Zustand, or similar client data layers.
- Experience developing B2B SaaS platforms with AI-powered features for enterprise customers.
- Background in knowledge management systems or enterprise search platforms.
- DevOps experience including containerization (Docker), CI/CD for AI systems, and feature flag implementations.
- Experience in early-stage startup environments with rapid iteration and product launches.
What We Offer
- Competitive USD-based compensation packages.
- AI-driven, innovation-focused projects.
- A culture that encourages curiosity and lifelong learning.
- Clear career paths toward Senior/Principal AI Engineer or AI Team Lead.
- Professional development opportunities to stay current with the rapidly evolving AI landscape.
- A flexible, work-from-home setup as part of a globally connected team.
- The stability of an established 16-year eCommerce company combined with the agility of an early-stage product team.
- A small, collaborative team environment working on complex, cutting-edge problems.
Join us to build a global product from the ground up and redefine how businesses run with AI.
