Senior Applied AI Scientist

Senior Applied AI Scientist – Generative AI & Agentic Systems Messagepoint is a privately‑owned software company providing an AI‑powered SaaS solution that enables enterprises to manage and personalize customer communications with greater speed, accuracy, and control. Our award‑winning platform empowers business users to create and optimize compliant, personalized communications across digital and print channels using advanced content intelligence and large language models. Messagepoint is headquartered in Toronto with employees located throughout Canada, the United States and the United Kingdom. About the Role Join the MARCIE AI Platform team to build production‑grade generative AI solutions that transform how enterprises handle customer communications. You'll bridge cutting‑edge research and production engineering—implementing state‑of‑the‑art LLM techniques, designing multi‑agent systems, and shipping scalable AI services that process multi‑modal, multi‑lingual communications at enterprise scale. Your ability to transform research insights into robust production systems will directly impact accuracy, speed, and safety for our customers. What You’ll Do Design and deploy production multi‑agent AI systems using LangGraph, OpenAI Assistants, or similar frameworks to solve complex business problems at production scale with comprehensive monitoring Build enterprise RAG pipelines implementing proven retrieval techniques (hybrid search, reranking, knowledge graphs) with measurable improvements in accuracy and performance Engineer prompts as versioned code using established techniques (Chain‑of‑Thought, ReAct) with systematic testing, evaluation pipelines, and CI/CD quality gates Stay current with AI research by reading papers from top conferences, evaluating emerging techniques for production viability, and implementing proven methods that deliver clear value Architect scalable agentic workflows with persistent state management, error recovery, observability (LangSmith, TruLens), and production‑grade reliability Integrate safety and compliance measures including PII detection, content filtering, guardrails, and optimize system performance through caching, model routing, and resource management Champion AI‑assisted development using tools like Claude Code, Augment, and Gemini CLI to accelerate engineering productivity and rapid iteration What You Bring (Must‑Haves) 5+ years of software engineering experience with 2+ years shipping LLM‑powered products to production with real users, SLAs, and monitoring MS in Computer Science or equivalent experience with strong foundation in deep learning, NLP, or machine learning; solid understanding of transformer architectures and modern techniques Ability to read and understand research papers to stay current and identify useful techniques for production implementation Production deployment of multi‑agent systems and RAG pipelines at scale using frameworks like LangGraph, OpenAI Assistants, with vector databases and retrieval optimization Expert‑level prompt engineering with systematic testing approaches, and strong software engineering practices (code review, testing, CI/CD) Python expertise with async programming, distributed computing experience (Spark, Ray, cloud storage), and active use of AI‑assisted development tools Cloud platform proficiency (AWS, GCP, or Azure) with experience in API design, microservices architecture, and production ML/AI infrastructure Nice to Have Experience with multimodal AI systems – vision‑language models, document understanding, and GraphRAG implementations Performance optimization expertise (quantization, fine‑tuning with LoRA/QLoRA) Publications, open‑source contributions, or conference participation Working knowledge of open‑source models via Hugging Face How We Work Workplace: Hybrid model with 1 or 2 days in the office, 3 or 4 days remote flexibility Team Culture: AI‑first engineering team using "Vibe Coding" (Claude Code, Augment, Gemini CLI) as essential productivity multipliers Tech Stack: OpenAI (primary), Gemini, AWS Bedrock | LangGraph, OpenAI Assistants, CrewAI | pgvector, Pinecone, Milvus | LangSmith, TruLens, OpenTelemetry | Python with FastAPI Focus: Generative AI and agentic systems for Customer Communications Management (CCM) – document processing, content understanding, semantic analysis at scale Resources: Access to latest AI models, robust compute infrastructure, and top‑tier development tools Conference Attendance: Support for attending major AI conferences to stay current with the field Interview Process Main Interview (90 mins) – system design, production AI experience, research understanding, and problem‑solving skills Hands‑on Test (in person) – practical assessment of your ability to build and optimize AI system components Messagepoint is an Equal Opportunity Employer and encourages diversity and inclusion in the workplace. We thank you for your interest, however, only those who qualify for an interview will be contacted. Seniority level Mid‑Senior level Employment type Full‑time Job function Information Technology Industries Software Development #J-18808-Ljbffr