Senior AI Engineer to design, build, and productionize agentic AI and LLM-powered solutions, including RAG, multi-step reasoning, and MCP server integration, for a digital banking client. Is this role right for you? In this role, you will:

Deliver and Scale Agentic AI Solutions:

Design, build, and productionize LLM-powered and agentic applications, including retrievalaugmented

generation (RAG), multi-step reasoning workflows, structured outputs, and prompt safety.

Build and consume MCP servers, defining schemas, endpoints, and access boundaries that enable safe,

scalable tool use.

Work hands-on to de-risk complex problems by writing, reviewing, and operating production-grade

AI systems.

Architect Secure, Reliable, and Observable Systems:

Partner closely with product, data, and engineering stakeholders to deliver AI capabilities that drive

tangible outcomes.

Apply strong fundamentals in structured and unstructured data, distributed systems, and service

integration.

Ensure systems are testable, observable, and resilient, with automated testing and transparent operational

feedback loops.

Design and operate secure, low-latency services and microservices with modern authentication and

authorization.

Contribute to architectural discussions, platform capabilities, and evolving best practices for AI

development.

Collaborate with platform and security partners to ensure systems meet enterprise risk, compliance,

and operational standards

Influence Technical Direction and Engineering Culture

Take ambiguous problems and translate them into clear technical solutions, communicating trade-offs

and constraints.

Model a culture of engineering excellence, inclusion, and continuous learning — digging into root

causes and sharing durable lessons.

Mentor peers through code reviews and design discussions, raising the bar for quality, ownership, and

long-term thinking.

Required Qualifications:

Extensive experience in Python and its core data science libraries (e.g., Scikit-learn, Pandas, NumPy,

Matplotlib/Seaborn).

Hands-on experience building LLM-powered applications — retrieval, agents, structured outputs,

Hands-on experience building and consuming MCP servers (designing endpoints, schemas, access

Strong experience in full stack fundamentals and microservices. Production experience with API

authentication and authorization (OAuth 2.0, OpenID Connect, and SAML) is required.





Deep understanding of structured and unstructured data management and their corresponding

technologies.

Proven experience in automated testing, including unit and functional testing, and the ability to

develop test strategies and design automation frameworks.

Preferred Qualifications:

Experience with Agentic AI frameworks and designing multi-step AI reasoning processes

Experience with MLOps principles and tools for model versioning (e.g., Git), containerization (e.g.,

Docker), and continuous integration/continuous deployment (CI/CD) of machine learning models

Strong theoretical and practical knowledge of classical machine learning algorithms (e.g.,

classification, regression, clustering, dimensionality reduction) and their applications in areas such as

Experienced with building and deploying NLP and voice response applications (including IVR and

Familiarity with Google's Vertex AI tech stack

Experience building applications with modern web component frameworks (such as React & Angular

Is this role right for you? In this role, you will:

Deliver and Scale Agentic AI Solutions:

Design, build, and productionize LLM-powered and agentic applications, including retrievalaugmented

generation (RAG), multi-step reasoning workflows, structured outputs, and prompt safety.

Build and consume MCP servers, defining schemas, endpoints, and access boundaries that enable safe,

scalable tool use.

Work hands-on to de-risk complex problems by writing, reviewing, and operating production-grade

AI systems.

Architect Secure, Reliable, and Observable Systems:

Partner closely with product, data, and engineering stakeholders to deliver AI capabilities that drive

tangible outcomes.

Apply strong fundamentals in structured and unstructured data, distributed systems, and service

integration.

Ensure systems are testable, observable, and resilient, with automated testing and clear operational

feedback loops.

Design and operate secure, low-latency services and microservices with modern authentication and

authorization.

Contribute to architectural discussions, platform capabilities,



and evolving best practices for AI

development.

Collaborate with platform and security partners to ensure systems meet enterprise risk, compliance,

and operational standards

Influence Technical Direction and Engineering Culture

Take ambiguous problems and translate them into clear technical solutions, communicating trade-offs

and constraints.

Model a culture of engineering excellence, inclusion, and continuous learning — digging into root

causes and sharing durable lessons.

Mentor peers through code reviews and design discussions, raising the bar for quality, ownership, and

long-term thinking.

Required Qualifications:

Extensive experience in Python and its core data science libraries (e.g., Scikit-learn, Pandas, NumPy,

Matplotlib/Seaborn).

Hands-on experience building LLM-powered applications — retrieval, agents, structured outputs,

prompt safety.

Hands-on experience building and consuming MCP servers (designing endpoints, schemas, access

boundaries)

Strong experience in full stack fundamentals and microservices. Production experience with API

authentication and authorization (OAuth 2.0, OpenID Connect, and SAML) is required.

Deep understanding of structured and unstructured data management and their corresponding

technologies.

Proven experience in automated testing, including unit and functional testing, and the ability to

develop test strategies and design automation frameworks.

Preferred Qualifications:

Experience with Agentic AI frameworks and designing multi-step AI reasoning processes

Experience with MLOps principles and tools for model versioning (e.g., Git), containerization (e.g.,

Docker), and continuous integration/continuous deployment (CI/CD) of machine learning models

Strong theoretical and practical knowledge of classical machine learning algorithms (e.g.,

classification, regression, clustering, dimensionality reduction) and their applications in areas such as

fraud detection, credit risk scoring, or customer segmentation

Experienced with building and deploying NLP and voice response applications (including IVR and

contact center intelligence)

Familiarity with Google's Vertex AI tech stack

Experience building applications with modern web component frameworks (such as React & Angular

Disclaimer: AI may be used in evaluating candidates. This posting is for an existing vacancy. #J-18808-Ljbffr

📌 Senior AI Engineer to design, build, and productionize agentic AI and LLM-powered solutions, includi (Toronto)
🏢 S.i. Systems
📍 Toronto