software engineer

N2P Systems; Toronto; On-site; Full time

Job summary

A leading technology company is seeking a skilled Gen AI Backend Engineer to design robust backend systems for Generative AI applications. This full-time role, based in Toronto, requires deep expertise in Python, Kubernetes, and Data Engineering. The ideal candidate has 6-8 years of experience and will work remotely while collaborating with cross-functional teams to develop intelligent systems. Competitive pay is offered, with an hourly rate of $50.

Qualifications

• 6–8 years of experience in backend engineering or software development.
• Strong expertise in Python and Kubernetes.
• Proven experience in Data Engineering.

Responsibilities

• Develop scalable and modular backend systems for Gen AI applications.
• Design and implement data ingestion pipelines to support AI/ML solutions.
• Collaborate with cross‑functional teams to build production‑grade AI products.

Skills

Python

Kubernetes

Data Engineering

LangChain

LangGraph

Azure Data Bricks

MongoDB

Job description

Posted on October 22, 2025 by Employer details N2P Systems

**Gen AI Backend Engineer** – Remote opportunity.

About the Role

We are seeking a highly skilled and motivated Gen AI Backend Engineer with deep expertise in Python, Kubernetes, and Data Engineering to design and build robust, scalable backend systems for Generative AI‑driven applications.

You will be instrumental in developing intelligent systems where Large Language Models (LLMs) control the application flow, leveraging frameworks such as LangChain, LangGraph, and Retrieval‑Augmented Generation (RAG).

Key Responsibilities

• Develop scalable and modular backend systems using Python and Kubernetes for Gen AI applications
• Design and implement data ingestion pipelines, Delta tables, and Azure Data Bricks workflows to support AI/ML solutions
• Build intelligent agent‑based systems using LangChain, LangGraph, and RAG, where LLMs decide control flow
• Work with AKS (Azure Kubernetes Service) to deploy and manage containerized Gen AI services at scale
• Integrate backend services with APIM, Azure Service Bus, and MongoDB for robust data exchange and service orchestration
• Ensure system performance, scalability, and security across the backend architecture
• Collaborate with cross‑functional teams including data scientists, DevOps, and product stakeholders to build production‑grade AI products
• Stay up to date on emerging Gen AI trends, tools, and best practices

Required Skills & Experience

• 6–8 years of experience in backend engineering or software development
• Strong expertise in Python and Kubernetes (design, deployment, scaling)
• Proven experience in Data Engineering: Azure Data Bricks, Delta Lake, data ingestion pipelines, and workflow orchestration
• Hands‑on experience with LangChain, LangGraph, or similar Gen AI frameworks
• Deep understanding of LLM‑based architectures and control flow‑driven design using RAG or MCP (Multi‑step Conversational Planning)
• Experience with Azure ecosystem: AKS, Azure APIM, Service Bus, and integration patterns
• Working knowledge of MongoDB for managing unstructured or semi‑structured data
• Familiarity with CI/CD pipelines, containerization best practices, and microservice architecture

Nice‑to‑Have

• Exposure to MLOps and Model Deployment Pipelines
• Experience building enterprise‑grade AI products or platforms
• Background in cloud cost optimization, monitoring, and logging (e.g., Azure Monitor, Prometheus, Grafana)
• Knowledge of security and compliance in AI/Cloud environments

Job Details

• Job Type: Full‑time
• Pay: $50.00 per hour
• Expected hours: 40 per week
• Location: Toronto, ON (On‑site)
• Salary: $50.00 HOUR hourly
• Terms of employment: Full time
• Starts as soon as possible
• Vacancies: 1
• Source: indeed.com #9915210669