Senior AI Developer — AI Agents

Posted Yesterday
Be an Early Applicant
Montréal, QC, CAN
In-Office
97K-160K Annually
Senior level
Automotive • Other
The Role
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.
Summary Generated by Built In

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.


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


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 :

  • Échelle salariale : de 97 000 $ CA à 160 000 $ CA. Les offres se situent rarement au sommet ou près du sommet de cette échelle. Le salaire réel sera établi en fonction de l’expérience et d’autres facteurs liés au poste.
  • 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:

  • Salary range: $97,000 CDN–$160,000 CDN. It is not typical for offers to be made at or near the top of the range. The actual salary will be determined based on experience and other job-related factors.
  • 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.

Skills Required

  • Experience building and owning a production service through design, release, and ongoing operation
  • Strong Python skills
  • Experience using large language models through prompting, tool access, and behavioral evaluation
  • Experience writing automated tests and conducting thoughtful code and design reviews
  • Ability to work effectively on evolving platforms with incomplete documentation
  • Ability to collaborate across disciplines and explain technical trade-offs
  • Deep TypeScript or Node.js expertise
  • Experience with language-model fine-tuning or reinforcement learning
  • Exposure to embedded or edge-system constraints
  • Experience with voice technologies, conversational interfaces, or automotive software
  • Hands-on experience using AI coding agents

Cerence Inc. Compensation & Benefits Highlights

The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Cerence Inc. and has not been reviewed or approved by Cerence Inc..

  • Healthcare Strength — Healthcare is described as strong and affordable, with mentions of a great health care plan and wellness support. Feedback suggests these offerings contribute to work-life balance and peace of mind.
  • Wellbeing & Lifestyle Benefits — Lifestyle perks such as gym membership reimbursement and transit subsidies are highlighted as meaningful add-ons. Feedback suggests these perks enhance the overall rewards package.
  • Strong & Reliable Incentives — Bonuses and equity incentives, including spot awards, short-term incentive targets, and ESPP, are cited as part of total rewards. Feedback suggests these programs are a notable component beyond base pay.

Cerence Inc. Insights

Am I A Good Fit?
beta
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.

The Company
HQ: Burlington, MA
1,288 Employees
Year Founded: 2019

What We Do

Cerence (NASDAQ: CRNC) is the global industry leader in creating unique, moving experiences for the mobility world. As an innovation partner to the world’s leading automakers and mobility OEMs, it is helping advance the future of connected mobility through intuitive, powerful interaction between humans and their cars, two-wheelers, and even elevators, connecting consumers’ digital lives to their daily journeys no matter where they are. Cerence’s track record is built on more than 20 years of knowledge and more than 400 million cars shipped with Cerence technology. Whether it’s connected cars, autonomous driving, e-vehicles, or buildings, Cerence is mapping the road ahead.

Similar Jobs

In-Office
Montréal, QC, CAN
1288 Employees
97K-160K Annually

Samsara Logo Samsara

Account Development Representative

Artificial Intelligence • Cloud • Computer Vision • Hardware • Internet of Things • Software
Easy Apply
Remote or Hybrid
Québec, QC, CAN
4000 Employees
65K-85K Annually

Samsara Logo Samsara

Account Development Representative

Artificial Intelligence • Cloud • Computer Vision • Hardware • Internet of Things • Software
Easy Apply
Remote or Hybrid
2 Locations
4000 Employees
82K-105K Annually

Block Logo Block

Implementation Specialist

Blockchain • eCommerce • Fintech • Payments • Software • Financial Services • Cryptocurrency
In-Office or Remote
8 Locations
12000 Employees
32K-63K Hourly

Similar Companies Hiring

Cravath, Swaine & Moore LLP Thumbnail
Legal Tech • Other • Professional Services
New York, NY
1200 Employees
Ford Energy Thumbnail
Automotive • Software • Energy • Utilities • Manufacturing • Renewable Energy
Glendale, Kentucky
55 Employees
Vega Thumbnail
Artificial Intelligence • Automotive • Insurance • Transportation
US
65 Employees

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account