To be discussed
Full-time · Remote from Egypt (Schedule sync with US time zones preferred)
We’re building an AI-native product that turns messy, real‑world information into clear, interactive experiences for end users. The details of the product and market will be shared in depth during conversations.
You’ll be a dedicated engineer owning the core technical stack: from LLM integration and retrieval pipelines to backend architecture and early product features. If you like taking a fuzzy product vision and turning it into a reliable, user-facing system, this role is for you.
Ingests and organizes heterogeneous data (documents, existing content, structured inputs).
Uses large language models and retrieval to generate and adapt content in response to user interactions.
Powers a conversational and search-like interface that can clarify, guide, and capture intent in real time.
Operates as a multi-tenant SaaS product with an API surface and embeddable interface components.
Design and implement LLM-powered flows for:
Ingesting and structuring unstructured content into a reusable internal model.
Generating and transforming text based on style and quality constraints (clarity, no fluff, concrete value).
Retrieval‑augmented interaction (RAG): grounding responses in stored data rather than hallucination.
Build and operate semantic retrieval infrastructure: embeddings, vector stores, chunking strategies, and ranking.
Architect and implement the initial multi‑tenant backend: auth, tenant isolation, core data models, and APIs.
Data ingestion and processing,
Real‑time interaction (chat/search style),
Configuration and simple analytics.
Choose and manage data stores (relational DB + vector store) and deploy to a major cloud provider.
Collaborate directly with the founder to design and implement the first-time user experience: from initial setup to “aha moment” where the system delivers real value in minutes.
Implement lightweight but high‑leverage UI surfaces (or APIs powering them) for configuration, rapid iteration, and inspection of AI outputs.
Iterate quickly based on early customer feedback and pilots; own the quality and reliability of features in production.
Implement robust LLM integration patterns: retries, timeouts, observability, and cost awareness.
Set up basic evaluation loops for AI behavior: quality checks, guardrails, and monitoring to catch regressions early.
Help define the technical roadmap and sequence of bets.
Establish early engineering practices (code quality, testing, reviews, deployment).
Contribute to future hiring by helping assess and onboard additional engineers.
Professional software engineering experience building and shipping production systems.
Hands‑on experience building LLM‑powered features (OpenAI / Anthropic / similar) beyond simple demos: prompt design, context management, and integration in a real product.
Strong backend skills in Python or Node.js (comfortable owning a modern web backend).
Practical experience with retrieval / vector search (e.g., pgvector, Pinecone, Weaviate, FAISS, Chroma) and building RAG-like workflows.
Solid understanding of web application architecture: HTTP APIs, auth, relational databases, caching, cloud deployment.
Strong builder mentality: you enjoy starting from zero, making architecture decisions, and iterating quickly.
Product‑oriented: you care about user impact and UX, not just model internals; comfortable working closely with non‑technical stakeholders.
Comfortable with ambiguity and changing requirements; can move forward with incomplete information as we iterate through development.
Clear communicator; able to explain tradeoffs and constraints in plain language.
Experience with modern frontend frameworks (React/Next or
similar).
Experience with content/knowledge/search products or conversational interfaces.
Prior startup / early-stage / founding-team experience.
Competitive salary commensurate with experience and stage.
Opportunity to grow into a senior or leadership role as the product and team scale.
In this role, the nature of the work is dynamic and requires a collaborative attitude. While you will have specific duties, it's important to understand that the entire team is responsible for the final delivery, and this may occasionally involve taking on additional tasks outside your primary responsibilities. The ability to adapt and contribute wherever needed is key to succeeding in this environment.
To apply for this job email your details to resumes@biblioso.com