Applied AI Engineer

Location: Montréal, Québec

Work model: Hybrid, with day-one onboarding onsite and a minimum of 3 days per week in the office

Experience level: Mid-level, generally 3 to 7 years depending on hands-on Generative AI experience

Industry: Financial services and enterprise technology

About the opportunity

Amaris Consulting is looking for an Applied AI Engineer to join a Generative AI engineering team supporting the adoption of AI across a leading global financial-services organization.

The team works with internal business and technology groups to identify, design, prototype, and validate high-value AI use cases that improve productivity, automate workflows, support decision-making, and create new business capabilities.

This is a hands-on engineering role focused on building prototypes, AI-powered applications, reusable components, enterprise integrations, and practical implementation patterns that help application teams move Generative AI solutions toward production.

The role The Applied AI Engineer will work closely with business stakeholders, application development teams, and enterprise AI platform teams.

You will act as a bridge between foundational AI capabilities and application teams by helping translate business needs into secure, scalable, and production-ready solutions.

Key responsibilities

- Work with business and technology stakeholders to understand Generative AI use cases and translate requirements into practical implementations.
- Develop proofs of concept, prototypes, reference applications, copilots, assistants, and AI-powered workflows.
- Build AI applications using enterprise AI platforms, models, APIs, and shared services.
- Implement Retrieval-Augmented Generation solutions using:
- Enterprise knowledge repositories
- Vector databases
- Embeddings
- Semantic search
- Retrieval pipelines
- Develop AI agents and orchestration workflows using frameworks such as:
- LangGraph
- LangChain
- Semantic Kernel
- Claude Code SDK
- OpenAI SDK
- Similar technologies
- Implement prompt-engineering techniques, structured outputs, tool calling,



context management, and workflow orchestration.
- Build APIs, connectors, and integrations between AI applications, enterprise systems, data platforms, and business workflows.
- Create reusable components, templates, implementation patterns, and developer examples.
- Develop automated testing and evaluation capabilities to measure:
- Quality
- Grounding
- Reliability
- Safety
- Accuracy
- Performance
- Troubleshoot implementation issues and support application teams as prototypes transition toward production.
- Collaborate with enterprise AI platform teams to follow engineering, security, governance, and Responsible AI standards.
- Stay current with emerging Generative AI technologies and apply relevant tools to business challenges.
- Contribute to technical documentation, knowledge sharing, and internal enablement activities.

Required qualifications

- Approximately 3 to 7 years of software engineering experience, with strong hands-on application-development responsibilities.
- At least 1 to 3 years of practical experience developing Generative AI applications, AI assistants, AI agents, copilots, or intelligent automation solutions.
- Strong proficiency in Python.
- Experience building APIs, integrations, and enterprise applications.
- Working knowledge of:
- Large Language Models
- Prompt engineering
- Embeddings
- Vector databases
- Semantic search
- Retrieval-Augmented Generation
- AI application architecture
- Hands-on experience with one or more AI development frameworks, such as LangGraph, LangChain, Semantic Kernel, Claude Code SDK, OpenAI SDK, or similar tools.
- Familiarity with Model Context Protocol, AI gateways, agent-to-agent communication, or tool-calling frameworks.




- Experience developing AI agents, orchestration workflows, tool integrations, or agentic applications.
- Experience building proofs of concept, prototypes, reference implementations, or internal accelerators.
- Experience integrating applications with enterprise systems, data platforms, and APIs.
- Familiarity with automated testing and evaluation for AI quality, safety, reliability, and performance.
- Awareness of Responsible AI principles, AI governance, security controls, and enterprise data-protection requirements.
- Experience with GitHub, CI/CD pipelines, containers, and modern software-engineering practices.
- Familiarity with Azure or AWS services used to host and operate applications and AI workloads.
- Ability to work effectively with business stakeholders and application-development teams.
- Strong communication, collaboration, problem-solving, and technical documentation skills.

Preferred qualifications

- Experience with Azure AI Foundry, AWS Bedrock, Anthropic Claude, OpenAI GPT models, Gemini, or comparable enterprise AI platforms.
- Experience building:
- RAG solutions
- Knowledge assistants
- AI-powered search tools
- Enterprise copilots
- Exposure to multi-agent systems and agent orchestration.
- Experience integrating AI applications with:
- ServiceNow
- Jira
- Confluence
- SharePoint
- Microsoft Graph
- Databricks
- Snowflake
- Similar enterprise platforms
- Familiarity with Kubernetes, containerized deployments, and cloud-native architectures.
- Experience in financial services or another regulated industry.
- Experience with monitoring, observability, prompt evaluation, model evaluation, or AI safety testing.

Why join this opportunity?

This is an prospect to work at the intersection of software engineering, Generative AI, enterprise architecture, and business transformation. You will help teams move from AI experimentation to practical implementation while contributing to reusable technologies and responsible AI adoption across a complex global organization.

📌 Applied AI Engineer (Montreal)
🏢 Mantu
📍 Montreal