Applied AI Engineer

MANNARINO; Montreal (administrative region); Hybrid; CAD 90,000 - 130,000; Full time

Benefits offered by this job

Group insurance

RRSP plan

Flextime with overtime

Discretionary bonuses

Fitness reimbursement

Catered weekly lunches

Free beverages

Company outings

Job summary

MANNARINO Systems & Software Inc. is seeking an Applied AI Engineer to help implement secure, reliable AI-assisted workflows for engineering and business activities.

You will work with IT, engineering and business stakeholders to deliver practical AI-enabled software solutions while focusing on reliability and traceability. The role emphasizes deploying internal GPU-based model serving, developing retrieval systems, and integrating AI tools with internal systems using MCP and standard APIs.

Qualifications

• Diploma or degree in Computer Science, Software Engineering, Computer Engineering, Data Science or related discipline, or equivalent practical experience.
• Strong proficiency in Python and experience developing maintainable applications, services or automation tools.
• Experience with Linux, Docker and Git.
• Experience working with APIs and integrating data across systems.
• Hands-on experience developing LLM-enabled applications using commercial, local or open-weight models.
• Experience building AI-assisted workflows that combine model outputs with contextual or retrieved information.
• Ability to evaluate AI outputs, identify inaccuracies or ungrounded responses and improve reliability through testing and validation.
• Demonstrated experience building and maintaining software solutions beyond tutorials or proof-of-concept exercises.
• Strong attention to detail, documentation and traceability.

Responsibilities

• Deploy and operate open-weight LLMs on internal GPU infrastructure, including model serving and optimization.
• Build and maintain retrieval systems over company docs and codebases.
• Package and deploy AI applications using containerized software engineering practices.
• Integrate AI tools with internal systems via APIs and MCP.
• Develop AI-assisted workflows for engineering artifacts, reports and business research.
• Implement provenance logging, context management and validation rules.
• Design internal UIs that support day-to-day AI usage.
• Establish evaluation frameworks and automated testing for AI outputs.
• Identify weaknesses in AI workflows and drive continuous improvements.

Skills

Python

LLM-enabled apps

APIs

Software engineering

Testing and validation

Attention to detail

Education

Degree in Computer Science / related

Tools

Linux

Docker

Git

MCP

Vector databases

Job description

MANNARINO Systems & Software Inc. is a leader in providing safety-critical systems, software, hardware and certification engineering services to the aerospace, defense, space, simulation & power generation industries.
Our customer base is very large, covering traditional aerospace companies as well as new and exciting markets, including electric propulsion, Urban Air Mobility, Unmanned Aerial Vehicle and autonomous flight.
The MANNARINO culture is focused on high quality, hard work, professionalism and teamwork within a highly respectful, motivating atmosphere geared towards long-term business growth.
As a member of our team, you will benefit from:

• a comprehensive group insurance and RRSP plan
• a flextime policy with paid overtime
• discretionary bonuses
• a fitness reimbursement program
• other office perks such as catered weekly lunches and free hot beverages (espresso, coffee, hot chocolate and tea)
• regular company outings

Career Opportunity and Primary Roles / Responsibilities
We are seeking an Applied AI Engineer to help implement secure, reliable AI-assisted workflows for engineering and business activities. The successful candidate will report to the person leading the company's applied AI implementation program and will collaborate with engineering, IT and business stakeholders.
The role focuses on delivering practical AI-enabled software solutions using commercial and open-weight AI models. It does not involve foundation model research or developing new LLM architectures.
Primary Responsibilities

• Work with IT to deploy and operate open-weight LLMs on internal GPU infrastructure, including model serving, quantization, performance optimization and application reliability
• Build and maintain retrieval systems over company documentation and codebases, including ingestion, chunking, embeddings, vector search and reranking
• Package and deploy AI applications using sound software engineering and containerization practices
• Integrate AI-enabled tools with internal systems, including Atlassian products, requirements-management and configuration-management platforms, using MCP and standard APIs
• Develop AI-assisted workflows supporting engineering and business activities, such as drafting engineering artifacts, triaging problem reports, automating reports and performing business development research
• Implement prompt and model configuration, context management, structured outputs, validation rules, logging, error handling and access controls
• Design internal user interfaces that support practical day-to-day usage
• Implement provenance logging and traceability mechanisms for AI-generated outputs
• Build evaluation frameworks and automated testing for accuracy, groundedness, consistency, safety, latency and regression detection
• Identify weaknesses in AI workflows and implement continuous improvements

Required Competencies

• Diploma or degree in Computer Science, Software Engineering, Computer Engineering, Data Science or a related discipline, or equivalent practical experience
• Strong proficiency in Python and experience developing maintainable applications, services or automation tools
• Experience with Linux, Docker and Git
• Experience working with APIs and integrating data across systems
• Hands-on experience developing LLM-enabled applications using commercial, local or open-weight models
• Experience building AI-assisted workflows that combine model outputs with contextual or retrieved information
• Ability to evaluate AI outputs, identify inaccuracies or ungrounded responses and improve reliability through testing and validation
• Demonstrated experience building and maintaining software solutions beyond tutorials or proof-of-concept exercises
• Strong attention to detail, documentation and traceability

Asset Qualifications

• Experience with local or open-weight models such as vLLM, Ollama or llama.cpp
• Knowledge of Retrieval-Augmented Generation (RAG), embedding models, vector databases and rerankers
• Experience with agent frameworks, tool calling or Model Context Protocol (MCP)
• Familiarity with knowledge graphs or GraphRAG
• Experience developing internal web applications and user interfaces
• Knowledge of automated testing, observability and secure application development
• Experience handling public, proprietary, confidential and controlled information appropriately

Miscellaneous Requirements

• Work can be done remotely.
• For employees based in Montreal, the work model is hybrid (at least one day at the office).
• The position may require occasional travel within North America.
• This position is open only to Canadian citizens and permanent residents currently residing in Canada.

Why this Role is Worth Your Time

• Real hardware. You will work with dedicated high-memory GPU infrastructure, not only a metered API key. Running models on hardware the organization controls - and dealing with what that actually involves - is a valuable skill that many engineers do not get to develop
• Scope. Small team, broad remit and direct access to the people making decisions. What you build is intended for real use, and feedback will be direct
• A hard domain. Safety-critical aerospace imposes constraints most AI work never encounters: traceability, reproducibility and evidence that may need to stand up to scrutiny years later. Learning to build AI systems within those constraints is genuinely differentiating
• An opportunity to help shape the direction. The architecture and implementation approach are still being developed

At MANNARINO, we believe that passion and a desire to learn is crucial. Diversity of thought and experiences leads to innovative solutions and creativity. This is why we would like to encourage all those interested to apply.
We are an equal opportunity employer. All applicants will be held in strict confidence. Only those selected for interview will be contacted.