LLM Engineer (GenAI)

Join our fast-paced team as an LLM Engineer (GenAI) and help build the next generation of AI tools that enhance critical thinking for humanity. You'll fine-tune and evaluate state-of-the-art language models, optimize prompts, develop multi-agent workflows, and improve AI agents using observability and experimentation tools. You'll also work closely with product and design teams to create intuitive applications that have a positive societal impact. Benefits include health, dental, and mental health benefits, flexible PTO, regular company retreats, mentorship opportunities, hybrid work in Toronto and NYC offices, and equity.

• Concevoir et développer des outils d'IA de nouvelle génération qui préservent et améliorent la pensée critique.
• Affiner et évaluer des modèles de langage à la pointe de la technologie, optimiser les invites pour maximiser la précision de la classification.
• Développer des flux de travail multi-agents incorporant des données provenant de diverses sources en utilisant RAG.
• The ideal candidate is someone who is adept at creating reliable AI agents, prompt engineering, possesses a great product sense, and is also an excellent software engineer
• Ability to wear multiple hats and be a leader as our team grows
• Excellent software engineer with experience building highly extensible and modular codebases, as well as complex pipelines
• Strong exploratory data analysis (EDA) skills to effectively leverage data in a way that informs pragmatic solutions
• 3+ YOE in Python
• Highly motivated to make positive societal impact
• 1+ YOE in LLM framework like Langchain or LlamaIndex
• 1+ YOE with agentic or RAG applications
• Self-starter (pitch, plan, and implement as a project owner in a fast-paced team)
• Experience pushing the cutting-edge in LLM abilities on novel tasks with subjective outputs
• Visa for work in Canada or US
• Strong open-source portfolio
• Publications at top-tier ML venues
• Experience working in an early-stage startup environment
• Experience with a prompt optimization framework like DsPY or TextGrad