Cerence Inc. Logo

Cerence Inc.

Senior AI Developer — AI Agents

Posted 12 Days Ago
Be an Early Applicant
In-Office
Montréal, QC, CAN
Senior level
In-Office
Montréal, QC, CAN
Senior level
Build and own domain-specific AI agents for Cerence’s automotive assistant platform, from design through production deployment. Responsibilities include LLM prompting, function and tool calling, retrieval, conversational handling, cloud and edge compatibility, automated testing, behavioral evaluation, and production quality improvement. The role partners with product teams to translate user experience goals into reliable conversational agents.
The summary above was generated by AI

AI That Moves the World. Careers That Move You Forward.
At Cerence AI, you’ll help transform advanced AI into trusted, real-world solutions that make complex technology – think vehicles, robots, smart manufacturing, and emerging intelligent devices – more natural, reliable, and useful. Building on decades of innovation and global deployment in automotive, we are extending our expertise into new products, markets, and intelligent systems. 

As part of our global team, you’ll work alongside leading innovators, researchers, engineers, and business leaders to solve meaningful challenges and turn breakthrough ideas into technology people use every day. You’ll have the opportunity to make a visible impact, help shape Cerence AI’s next chapter, and move your own career forward.


--------------------------------------------------------------


Job Description | Description du poste

Français canadien | English

Le rôle

Un bon modèle ne suffit pas, à lui seul, à créer un bon assistant. Il faut bâtir l’agent qui l’entoure — la couche qui détermine ce que le conducteur voulait dire, appelle la bonne fonction du véhicule, gère les questions de suivi et se rétablit avec élégance lorsqu’un problème survient à 100 km/h. Voilà l’essence de ce rôle. Vous serez responsable d’un domaine de l’assistant, vous développerez l’agent qui le prend en charge sur notre plateforme xUI™ et vous veillerez à ce qu’il fonctionne aussi bien dans le nuage qu’en périphérie.

Ce que vous ferez
  • Développer et prendre en charge l’un de nos agents spécialisés par domaine, de la conception au déploiement, puis sur le terrain
  • Concevoir l’interface d’appel de fonctions qu’un grand modèle de langage utilise pour accomplir des tâches concrètes — régler la climatisation, lancer une chanson ou définir une destination — et la rendre robuste face aux nombreuses façons dont un conducteur peut formuler sa demande
  • Faire fonctionner un même agent dans le nuage et en périphérie, tout en conservant une base de code commune plutôt que des versions distinctes
  • Intégrer les capacités des grands modèles de langage au comportement du produit : conception de requêtes, recherche d’information, sélection d’outils et gestion de conversations non linéaires
  • Maintenir un haut niveau de qualité grâce aux tests automatisés, à la mesure concrète du comportement des agents et à une réduction réelle du nombre d’anomalies
  • Travailler selon une approche d’ingénierie agentique — les agents de programmation fondés sur l’IA sont au cœur de notre façon de développer, et nous voulons que vous contribuiez à faire progresser cette pratique
  • Collaborer avec l’équipe produit pour transformer une intention d’expérience utilisateur en un agent qui la traduit réellement dans son utilisation
Environnement technologique
  • Langages : Python, TypeScript
  • IA : intégration de grands modèles de langage — conception de requêtes, appels de fonctions et d’outils, génération augmentée par la recherche
  • Qualité : tests automatisés, évaluation comportementale de systèmes non déterministes
  • Méthodes de travail : Git, intégration continue et utilisation quotidienne d’agents de programmation fondés sur l’IA
Ce que vous apportez
  • Vous avez développé et pris en charge un service en production suffisamment longtemps pour assumer les conséquences de vos propres décisions de conception
  • Solide maîtrise de Python
  • Vous avez utilisé les grands modèles de langage comme composants de base — en concevant des requêtes, en leur donnant accès à des outils et en évaluant des comportements non déterministes
  • Vous avez un véritable souci de la qualité : vous rédigez des tests, effectuez des revues réfléchies et soulevez tôt les questions de conception difficiles
  • Vous êtes à l’aise de travailler sur une plateforme en évolution, où les réponses ne sont pas toujours encore documentées
  • Vous collaborez efficacement avec différentes disciplines et savez expliquer des compromis techniques à des personnes qui n’ont pas votre expertise
Atouts
  • Expertise approfondie en TypeScript ou Node.js
  • Expérience, même limitée, de l’adaptation de modèles de langage par réglage fin ou apprentissage par renforcement
  • Connaissance des contraintes des systèmes embarqués ou de périphérie : mémoire limitée, absence de réseau et exigences strictes en matière de latence
  • Expérience des technologies vocales, des interfaces conversationnelles ou des logiciels automobiles
  • Expérience pratique de l’utilisation d’agents de programmation fondés sur l’IA dans votre propre flux de travail
Ce que nous offrons

Nous offrons un généreux programme de rémunération et d’avantages sociaux, en plus du salaire de base, qui comprend notamment :


  • Possibilité de prime annuelle
  • Couverture d’assurance (soins médicaux, soins dentaires, soins de la vue, assurance vie et assurance invalidité)
  • Congés payés
  • Jours fériés payés
  • Cotisation de l’entreprise au REER canadien (régime enregistré d’épargne-retraite)
  • Attribution d’actions pour certains postes et niveaux
  • Possibilité de travail à distance ou hybride, selon le poste

Toute rémunération et tout avantage social sont assujettis aux modalités des régimes ou programmes applicables et peuvent être modifiés, supprimés ou remplacés périodiquement.

The Role

A good model doesn’t make a good assistant on its own. Someone has to build the agent around it — the layer that decides what the driver meant, calls the right vehicle function, handles the follow-up question, and recovers gracefully when something goes sideways at 100 km/h. That’s this role. You’ll own a domain of the assistant, build the agent that serves it on our xUI™ platform, and make it work in the Cloud and on the Edge alike.

What You’ll Do
  • Build and own one of our domain-specific agents, from design through release and into the field
  • Design the function-calling surface an LLM uses to actually do things — adjust the climate, queue up a song, set a destination — and make it robust to the many ways a driver might ask
  • Make a single agent work in the Cloud and on the Edge, keeping the codebase shared rather than forked
  • Integrate LLM capabilities into product behaviour: prompting, retrieval, tool selection, and handling conversations that don’t go in a straight line
  • Hold the quality line — automated tests, real measurement of agent behaviour, and driving bug counts down rather than around
  • Work in an Agentic Engineering workflow — AI coding agents are a core part of how we build here, and we want you helping push that further
  • Partner with product to turn a UX intention into an agent that genuinely feels that way to use
Tech Stack
  • Languages: Python, TypeScript
  • AI: LLM integration — prompting, function and tool calling, retrieval-augmented generation
  • Quality: automated testing, behavioural evaluation of non-deterministic systems
  • Workflow: Git, CI, and AI coding agents as a daily tool
What You Bring
  • You’ve built and owned a production service, and stayed with it long enough to live with your own design decisions
  • Strong Python
  • You’ve worked with LLMs as building blocks — prompting them, giving them tools, and evaluating behaviour that isn’t deterministic
  • You have a real quality instinct: you write the tests, you review thoughtfully, and you raise the awkward design question early rather than late
  • You’re comfortable building on a platform that’s still evolving, where the answer isn’t always documented yet
  • You work well across disciplines and explain technical trade-offs to people who don’t share your background
Nice to Have
  • Depth in TypeScript or Node.js
  • Experience adapting language models through fine-tuning or reinforcement learning, even lightly
  • Exposure to embedded or edge constraints: limited memory, no network, hard latency budgets
  • Background in voice, conversational interfaces, or automotive software
  • Hands-on experience using AI coding agents in your own workflow

What We Offer

We offer a generous compensation and benefits package, in addition to the base salary, including:


  • Annual bonus opportunity
  • Insurance coverage (medical, dental, vision, life, and disability)
  • Paid time off
  • Paid holidays
  • Company contribution to the CDN RRSP (Registered Retirement Savings Plan)
  • Equity awards for certain positions and levels
  • Remote and/or hybrid work available depending on the position

All compensation and benefits are subject to the terms and conditions of the underlying plans or programs, as applicable, and may be amen terminated, or replaced from time to time.

Cerence AI (NASDAQ: CRNC) helps people and intelligent systems work together naturally and reliably. Proven at global scale in automotive, Cerence provides the trusted interaction and action layer connecting people, machines, and intelligent systems. Its AI platform enables natural interaction and dependable action across complex real-world environments where reliability, safety, security, and performance are critical. Working with customers and partners worldwide, Cerence transforms advanced AI into trusted solutions that bridge the gap between AI potential and real-world performance.


For more information, visit www.cerence.ai.


EQUAL OPPORTUNITY EMPLOYER

Cerence is firmly committed to Equal Employment Opportunity (EEO) and to compliance with all federal, state and local laws that prohibit employment discrimination on the basis of age, race, color, gender, gender identity, gender expression, sex, sex stereotyping, pregnancy, national origin, ancestry, religion, physical or mental disability, medical condition, marital status, citizenship status, sexual orientation, protected military or veteran status, genetic information and other protected classifications. Cerence Equal Employment Opportunity Policy Statement.


All prospective and current Employees need to remain vigilant when it comes to executing security policies in the workplace. This includes:

- Following workplace security protocols and training programs to familiarize with the ways to maintain a safe workplace.
- Following security procedures to report any suspicious activity.
- Having respect for corporate security procedures to allow those procedures to be effective.
- Adhering to company's compliance and regulations.
- Encouraging to follow a zero tolerance for workplace violence.

- Basic knowledge of information security and data privacy requirements (e.g., how to protect data & how to be handling this data).

- Demonstrative knowledge of information security through internal training programs.

Cerence Inc. Montréal, Québec, CAN Office

1500 Boulevard Robert-Bourassa, Montréal, Canada, H3A 3S8

Similar Jobs

12 Days Ago
In-Office
Montréal, QC, CAN
Senior level
Senior level
Automotive • Other
Build and own domain-specific AI agents for Cerence’s automotive assistant platform. Responsibilities include designing LLM function-calling interfaces, integrating prompting, retrieval, tool selection, and conversational handling, and deploying shared agents across cloud and edge environments. The role emphasizes automated testing, behavioral evaluation, production reliability, collaboration with product teams, and agentic engineering practices.
Top Skills: Ai Coding AgentsAutomated TestingBehavioral EvaluationContinuous IntegrationEmbedded SystemsFine-TuningFunction CallingGitLarge Language ModelsNode.jsPrompt EngineeringPythonReinforcement LearningRetrieval-Augmented GenerationTool CallingTypescriptXui
3 Hours Ago
Easy Apply
Remote or Hybrid
Canada
Easy Apply
Junior
Junior
Artificial Intelligence • Cloud • Computer Vision • Hardware • Internet of Things • Software
Lead and develop a Canada Scaled Customer Success team to drive onboarding, adoption, expansion, and renewals via digital scale programs. Hire and coach CSMs, manage KPIs/OKRs, improve processes and tooling, collaborate cross-functionally, and escalate high-stakes customer moments to ensure measurable customer outcomes.
Top Skills: CRMCs PlatformDigital Engagement ToolsGainsightProduct AnalyticsTotango
14 Hours Ago
Hybrid
Montréal, QC, CAN
Junior
Junior
Biotech • Consulting • Pharmaceutical
The Junior CRM & Business Development Associate supports CRM operations and business development activities, including maintaining the HubSpot database, outreach efforts, meeting coordination, and utilizing AI tools for productivity.
Top Skills: ChatgptClaudeHubspotExcelMicrosoft Word

What you need to know about the Montreal Tech Scene

With roots dating back to 1642, Montreal is often recognized for its French-inspired architecture and cobblestone streets lined with traditional shops and cafés. But what truly sets the city apart is how it blends its rich tradition with a modern edge, reflected in its evolving skyline and fast-growing tech industry. According to economic promotion agency Montréal International, the city ranks among the top in North America to invest in artificial intelligence, making it le spot idéal for job seekers who want the best of both worlds.

Key Facts About Montreal Tech

  • Number of Tech Workers: 255,000+ (2024, Tourisme Montréal)
  • Major Tech Employers: SAP, Google, Microsoft, Cisco
  • Key Industries: Artificial intelligence, machine learning, cybersecurity, cloud computing, web development
  • Funding Landscape: $1.47 billion in venture capital funding in 2024 (BetaKit)
  • Notable Investors: CIBC Innovation Banking, BDC Capital, Investissement Québec, Fonds de solidarité FTQ
  • Research Centers and Universities: McGill University, Université de Montréal, Concordia University, Mila Quebec, ÉTS Montréal

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account