Senior AI Engineer / AI Agent Lead

Senior AI Engineer / AI Agent Lead Emplia Inc. Montréal, QC | Full-Time | Hybrid Reports to: Head of Product About Emplia Emplia is building an AI-powered workforce support platform designed to transform how employees interact with HR, Time & Attendance, Payroll, and other enterprise workforce systems. At the center of our platform is the Emplia Agent — a multilingual conversational AI that provides employees and managers with a single, intelligent entry point to workforce information, enterprise systems, and validated organizational knowledge. Unlike a general-purpose chatbot, the Emplia Agent is designed for enterprise environments where accuracy, security, permissions, privacy, traceability, and controlled actions matter. We are moving from Proof of Concept toward MVP and are looking for a senior AI engineerto take technical ownership of the Emplia Agent. The Role As Senior AI Engineer / AI Agent Lead, you will be responsible for the architecture, development, testing, and continuous improvement of the intelligence layer behind the Emplia Agent. Reporting to the Head of Product, you will work closely with product, engineering, HR technology specialists, and external technology providers to translate product requirements into a reliable, secure, and scalable AI agent. This is a highly hands-on position. You will not simply configure an LLM or write prompts. You will own how the Agent reasons, retrieves information, interacts with enterprise systems, applies permissions and guardrails, uses tools, handles uncertainty, escalates cases, and delivers consistent multilingual experiences. What You Will Own You will take technical ownership of the Emplia Agent, including: Design and development of the core conversational AI architectureLLM integration, evaluation, and model-selection strategyRetrieval-Augmented Generation (RAG) architectureVector and hybrid searchKnowledge retrieval, grounding, and source citationPrompt, system-instruction, and context architectureAgent skills and reusable AI capabilitiesIntent recognition and request classificationAI tool use and function callingAgent orchestration and workflow logicRead versus transactional action routingExplicit confirmation workflows for sensitive or transactional actionsGuardrails and controlled refusal behaviorHuman escalation and exception handlingHallucination prevention and factuality controlsPermission-aware retrieval and data accessMultilingual AI behaviorSpeech-to-Text and Text-to-Speech integrationAI observability, tracing, and monitoringAI evaluation and regression testingLatency, reliability, and AI cost optimizationPrivacy-aware handling of PII and conversational contextTechnical documentation of AI architecture and design decisions The Product Challenges You Will Help Solve The Emplia Agent is being designed to operate across complex enterprise environments. Some of the challenges you will work on include: Providing answers exclusively from approved enterprise knowledge and authorized system dataPreventing unsupported or fabricated answersDynamically retrieving information from HR and workforce systemsEnsuring employees only access information they are authorized to seeDetecting conflicting data across enterprise systemsKnowing when the Agent should answer, ask a clarification question, execute an action, or escalate to a humanCreating safe confirmation workflows before transactional actions are executedSupporting enterprise HR processes across multiple systems and clientsMaintaining strict tenant and data isolationDelivering consistent experiences across text and voiceSupporting English, French, Spanish, and FinnishRecognizing regional language variations, including Canadian FrenchBuilding a framework that allows new Agent skills and enterprise integrations to be added over time What We're Looking For Required Strong professional software engineering experienceHands-on experience developing production applications using Large Language ModelsStrong Python development skillsExperience working with commercial LLM APIs or platforms such as OpenAI, Azure AI, Anthropic Claude, Google Gemini, or equivalentStrong understanding of Retrieval-Augmented Generation (RAG)Experience with vector databases, embeddings, semantic search, and/or hybrid searchExperience implementing LLM tool use / function callingExperience building conversational AI, AI agents, or agentic workflowsStrong API and backend development skillsExperience combining LLM reasoning with deterministic application logicExperience developing automated evaluation frameworks for AI applicationsUnderstanding of authentication, authorization, and permission-aware systemsUnderstanding of AI hallucination, grounding, confidence, and failure modesExperience handling sensitive or enterprise dataExperience with AI application logging, tracing, monitoring, and production troubleshootingStrong problem-solving and software architecture skills Strong Assets Experience with one or more of the following would be particularly valuable: Microsoft AzureMicrosoft Foundry / Azure AIAzure OpenAIAzure AI SearchAzure SpeechOpenAI APIsPostgreSQL / pgvectorSemantic and hybrid retrievalEnterprise searchSpeech-to-TextText-to-SpeechReal-time conversational AIMultilingual NLPEnterprise SaaSMulti-tenant applicationsEnterprise integrations and APIsHR technology or HRIS platformsUKGWorkdaySAP SuccessFactorsOracle HCMDayforceADPJira APIsPII-sensitive applicationsEnterprise security and compliance environmentsPrevious HR technology experience is valuable but not required. You will work closely with internal workforce technology and product experts. What Success Looks Like During your first months at Emplia, you will: Take ownership of the existing Emplia Agent architecture and AI codebaseEstablish a structured AI evaluation and regression-testing frameworkValidate and optimize the LLM and retrieval architectureImprove grounding, factuality, source citation, and refusal behaviorImprove tool-calling reliability and exception handlingDevelop and refine Agent skills and guardrailsEstablish AI observability and quality metricsValidate multilingual performanceHelp evolve voice capabilitiesSupport the transition from POC to pilot deploymentLead the AI engineering workstream toward MVPEstablish engineering standards that allow the Emplia Agent to scale across additional clients, systems, languages, and workforce use cases Who You Are You enjoy solving problems that sit between AI research and real-world software engineering. You understand that a production enterprise AI agent is much more than a prompt connected to an LLM. You care about reliability, architecture, testing, security, and user experience. You are comfortable experimenting with new AI technologies but equally comfortable deciding when deterministic software is safer and more appropriate than AI. You are able to take ownership of a problem, propose a solution, build it, test it, measure it, and improve it. And you want the opportunity to help shape an AI product from its early stages into a production enterprise platform. Why Join Emplia This is an opportunity to join Emplia at a pivotal stage as we move from Proof of Concept toward MVP and commercial deployment. You will have significant influence over: The architecture of the Emplia AgentOur AI technology stackHow Agent skills are designedOur AI engineering standardsHow AI interacts safely with enterprise workforce systemsOur multilingual and voice strategyThe future AI engineering teamRather than maintaining one small component of a mature platform, you will have the opportunity to take ownership of the intelligence behind the product and help build Emplia's AI engineering capability from the ground up. Apply If you're passionate about building reliable enterprise AI agents and want to take meaningful ownership of a product from POC through MVP and scale, we'd like to hear from you. Send us your CV or LinkedIn profile and tell us about an AI application or agent you've built that you're particularly proud of.