Data Scientist

• Build and improve AI-powered applications using LLMs, foundation models, and modern AI APIs
• Integrate commercial and open-source language models using prompting strategies, structured outputs, tool calling, and model selection
• Develop RAG pipelines for retrieving and reasoning over information from documents, databases, and unstructured data
• Build and experiment with AI agents and multi-step workflows
• Develop document ingestion, text extraction, chunking, embeddings, metadata management, and semantic search pipelines
• Evaluate AI outputs and build test datasets and evaluation workflows
• Integrate AI capabilities into APIs and existing product workflows with backend engineers
• Optimize model selection, caching, retrieval strategies, prompts, latency, reliability, and inference costs
• Investigate AI pipeline issues, troubleshoot model behaviour, and monitor AI feature quality and performance
• Evaluate emerging AI tools and frameworks and translate customer problems into practical AI solutions

• 1–3 years of experience in AI engineering, machine learning engineering, software engineering, or a related field
• Strong internships and hands-on projects involving AI applications are valuable
• Proficiency in Python and ability to write clean, modular, maintainable code
• Understanding of LLM application fundamentals, including prompting, context windows, token limits, structured outputs, and common failure modes
• Familiarity with embeddings, vector search, document retrieval, and RAG-based applications
• Experience with REST APIs, JSON, asynchronous operations, and external service integration
• Ability to work with structured and unstructured data using Pandas and SQL
• Ability to test application behaviour systematically, investigate failures, and improve AI workflow reliability
• Experience with or familiarity in production LLM applications, AI agents, tool/function calling, LangChain, LangGraph, LlamaIndex, vector databases, search technologies, evaluation frameworks, tracing, monitoring, Docker, cloud platforms, deployment workflows, document intelligence, B2B SaaS, enterprise AI, or AEC and revenue operations
• Clear communication, openness to feedback, and effective collaboration with engineering and product stakeholders