AI Developer - LLM Features & AI Systems

We're looking for an AI Developer to build the AI backbone of our product — retrieval-augmented generation pipelines, multi-step agent workflows, embedding systems, and LLM integrations that property managers rely on daily. You'll work directly with product and engineering to ship AI features end-to-end: designing vector search strategies, building agent loops, evaluating model quality, and shipping systems that actually work in production. You won't just execute tickets — you'll bring a point of view on embedding models, chunking strategies, reranking approaches, and the real tradeoffs between quality, latency, and cost. This position is based in North York and is currently full-time in-office. This position is ideal for someone who thrives in a collaborative, high-energy environment and enjoys building teams in person.** About Us:** STAN is the largest provider of AI solutions for HOA and Condo Property Managers. We are using cutting-edge and patented artificial intelligence technology to build solutions that enhance life for residents of more than 4 million+ homes across North America. And, we are on a mission to build the world’s first AI property manager. Want to come along for the ride? STAN is also an award-winning platform, having been recognized by Rogers, FedEx, George Brown College, StartUp Canada, the Waterloo Accelerator Centre, and more! To learn more, feel free to visit us at www.stan(.)ai 🤖 Tasks RAG Pipelines: Design and build retrieval-augmented generation systems. Own chunking strategy, embedding selection, retrieval optimization, and reranking. Vector Databases: Implement and manage vector search infrastructure (Pinecone, Weaviate, or similar). Integrate embeddings with our MongoDB core data layer. Agent Workflows: Build multi-step agent loops with tool use, memory, planning, and guardrails. Handle edge cases like hallucination, context limits, and reasoning failures. LLM Integration: Integrate Claude and OpenAI APIs using orchestration frameworks (LangChain, LlamaIndex, or equivalent). Manage prompts, context windows, streaming, function calling, and tool use. Evals & Quality: Build evaluation pipelines to measure LLM output quality. Iterate on prompts, retrieval strategies, and model choices based on real data. AI Tooling & Developer Experience: Use Claude Code and modern AI-assisted development as part of your workflow. Help the team ship faster with AI tools.Collaboration & Architecture: Work with product to scope AI features and advise on feasibility. Help set patterns and best practices as the AI feature set grows. Requirements Must Have: Hands-on experience building RAG systems in production (chunking, embedding, retrieval, reranking) Real experience with embedding models (OpenAI, Cohere, or open-source) and vector databases (Pinecone, Weaviate, Chroma, or similar) Experience building agent loops or multi-step reasoning systems (tool use, memory patterns, error handling) Familiarity with Claude API and/or OpenAI API — prompt design, function calling, streaming Strong TypeScript and Python — you write clean, maintainable, well-tested code Understanding of LLM limitations: hallucination, context windows, latency, inference cost, and real-world tradeoffs Strong Assets: Experience with Claude Code or AI-assisted development workflows Knowledge of LLM evaluation frameworks (RAGAS, custom metrics, semantic similarity scoring) Side projects or portfolio demonstrating real AI work (not tutorials) — GitHub, demos, case studies Hands-on experience with orchestration frameworks (LangChain, LlamaIndex, or equivalent) Experience with multi-modal inputs or structured output extraction (JSON mode, schema validation) Background shipping AI features in a production SaaS environment (not just experiments) Familiarity with Stan AI stack: Node.js, TypeScript, MongoDB, AWS Understanding of prompt engineering, few-shot learning, and in-context optimization Nice to Have: Fine-tuning or RLHF experience Contributions to open-source AI projects Experience in PropTech, FinTech, or operations software Knowledge of prompt injection risks and AI safety patterns Familiarity with vector database administration (indexing, cost optimization, scaling) Benefits Competitive salary Comprehensive health, dental, and specialist benefits. Company Macbook. Free parking and shuttle service to the office. Extra PTO during occasional US holidays. Company events, in-office restaurant, and building-wide perks. Unlimited ping pong and espresso! Most "AI developer" roles mean adding a ChatGPT call to an existing feature. This is different. You'll be building the AI backbone of a product that property managers depend on daily to run their business. You'll make real architectural decisions: embedding models, retrieval strategies, chunking approaches, evaluation metrics. You'll see the results ship and hear directly from customers.

You will design and build the AI backbone of the product, including RAG pipelines, multi-step agent workflows, and embedding systems. You will also collaborate with product and engineering teams to evaluate model quality and ship AI features into production.

Candidates must have hands-on experience building production-grade RAG systems, vector databases, and agent loops. Proficiency in TypeScript, Python, and working with LLM APIs like OpenAI or Claude is essential.

• Competitive salary • Comprehensive health benefits • Dental benefits • Specialist benefits • Company Macbook • Free parking • Shuttle service • Extra PTO • Company events • In-office restaurant • Building-wide perks • Unlimited ping pong • Espresso

• TypeScriptSouhaitée
• Amazon Web ServicesSouhaitée
• MongoDBSouhaitée
• PythonSouhaitée

Relevées dans la description du poste. Confirmez les exigences importantes ci-dessus.

• RAG pipelines
• Vector databases
• Agent workflows
• LLM integration
• TypeScript
• Python
• Prompt engineering
• Pinecone
• Weaviate
• LangChain
• LlamaIndex
• MongoDB
• AWS
• Evaluation frameworks
• Embedding models
• System architecture
• Hallucinations
• Claude Code
• PineCone
• ChatGPT
• Prompt Engineering
• Case Study
• Pipelines
• Energetic
• Vector Database
• Financial Technology (FinTech)
• Shipping Systems
• AI Safety
• Workflow Management
• Retrieval Augmented Generation
• Few Shot Learning
• Espresso Beverages
• Planning
• Application Programming Interface (API)
• Artificial Intelligence
• Amazon Web Services
• Software As A Service (SaaS)
• Exception Handling
• Tutorials
• Github
• JSON
• Python (Programming Language)
• Reasoning Systems
• Node.js (Javascript Library)
• Open Source Technology
• Operations
• Performance Metric
• Restaurant Operation
• Tooling
• Indexing

• Technology
• Software
• Engineering
• Data & Analytics
• Director of Artificial Intelligence
• Software Developer / Engineer
• Software Developers

Expérience minimale

2+ ans

Langue de l’offre

anglais

Heures de travail

40 heures par semaine