AI Infrastructure Engineer – BlueCat Horizon Platform

BlueCat
CA$160K - CA$180K/yr

Agentic Frameworks

Tech Stack

About the Role

We're BlueCat—a Great Place to Work for good reason. Our team solves critical network challenges for some of the world's largest organizations. In simple terms, we manage the systems that keep networks running smoothly, securely, and reliably—the backbone infrastructure that powers digital transformation for enterprises globally. Our Intelligent Network Operations platform delivers and enables AI-driven agentic ops at scale, automating and simplifying how companies manage, secure, and optimize their networks.

But what makes us different is how we work: we believe great work happens in an environment where you're trusted, heard, and supported. With teams globally, we're building a workplace culture that values collaboration and integrity as much as innovation. If you're looking to advance your career with a company that invests in its people, this is it.

Job Description:

The BlueCat Horizon team is responsible for powering all BlueCat SaaS products. Our mission is to deliver BlueCat products on a reliable, fast, globally distributed, and cost-effective enterprise-grade cloud infrastructure. Central to this mission is our AI first strategy, as we fully embrace a product model where AI is integral to everything we create.


The AI Infrastructure Engineer role is a high-impact, implementation-focused position centered on building a production-grade agentic platform for
Horizon. You will be lead coder for our autonomous agent runtime, leveraging Amazon Bedrock AgentCore as the core framework and Kubernetes (EKS) as the orchestration engine.

 

Key Responsibilities:

You will bridge the gap between "experimental agents" and "production systems." Your mission is to build the secure, scalable, and stateful infrastructure that allows agents to reason, access enterprise tools, and persist memory. You will spend the majority of your time writing Go for systems-level Kubernetes extensions and Python for the agentic framework logic.

You will be working closely with the Architecture Team, driving architectural decisions to implementation and operation, interact with the product management team to understand the use-cases, requirements and develop and present technical solutions. Your work will directly impact the scalability, performance, and reliability of the BlueCat Horizon Platform, ensuring that it meets the demanding needs of the versatile AI Agentic Workloads.

 

Responsibilities/Duties:

  • Runtime Implementation: Deploy and optimize the AgentCore Runtime on Amazon EKS, ensuring agents have a secure, high-performance environment for long-running tasks.
  • Secure Gateway Logic: Build the AgentCore Gateway using Go to mediate between autonomous agents and internal microservices, enforcing zero-trust security.
  • State & Memory Management: Architect persistent state layers, ensuring agents maintain context across sessions or specialized vector stores.
  • Platform Integration: Engineer the "connective tissue" between AgentCore and the Horizon Kubernetes platform, ensuring agents have native access to cluster resources and internal services.
  • Standardized Tooling: Leverage the Model Context Protocol (MCP) to integrate diverse data sources and internal tools into the agent ecosystem.
  • Secure Gateways: Build the "connective tissue" in Go or Python that allows agents to securely interact with enterprise APIs via the AgentCore Gateway.
  • Evaluation: Design and implement automated evaluation frameworks to verify that Horizon agents are performing tasks accurately, safely, and within BlueCat's operational guardrails.
  • Observability: Build the infrastructure to capture agent execution traces and user feedback, feeding it back into the evaluation pipeline to continuously improve agent reliability.
  • Horizon-Specific Tooling: Build secure, high-performance interfaces in Go and Python that allow agents to interact with Horizon APIs, telemetry data, and configuration engines.
  • IaC Mastery: Lead the implementation of Terraform or AWS CDK modules to deploy the full AgentCore stack (Identity, Memory, and Gateway) in a repeatable, multi-account fashion.
  • Provide the infrastructure support for Retrieval-Augmented Generation (RAG) systems, ensuring low-latency access to vector databases.
  • Knowledge Graph Support: Support the integration of Knowledge Graphs into the agent reasoning loop to provide structured enterprise context.

 

 

Qualifications

  • Bachelor’s degree in computer science, Engineering, or a related field; Master’s degree preferred.
  • 10+ years' experience in software engineering with around 5+ years commercial experience in cloud distributed systems and high scale designs with  Golang and async Python,
  • Hands-on experience with AWS AgentCore ( or similar Agentic AI platforms), Agent SDK (Strand, OpenAI, LangChain), protocols (MCP, A2A),
 
  • Agentic Expertise: Proven ability to move agents beyond "chat" into autonomous "action" loops (MCP, A2A, RAG, KnowledgeBase)
  • Must have 2+ years hands-on proficiency in Kubernetes, kubernetes operators and containers
  • Experience with Helm charts, API gateways, ingress/egress gateways
 
  • You are passionate about building great REST APIs (and helping others do the same). 
  • Passion for engineering rigor and operational excellence (design principles and patterns, unit testing, best practices for security and privacy, CI/CD etc).
  • Experience with CI/CD tools (GitLab) & automation
  • Strong experience with code tools like Terraform
  • Excellent written and verbal/presentation communication skills
  • Ability to work well with a distributed team

This position offers a salary range of 160,000 - 180,000 CAD per year plus participation in a discretionary bonus plan. Final compensation will be based on skills, experience, and qualifications.


The role is for an existing vacancy.
If you share our enthusiasm for the future of our company and are eager to contribute to our vibrant workplace, we look forward to receiving your application! Our comprehensive benefits encompass your health, financial well-being, and overall wellness, and we are committed to providing an exceptional work environment, enriching employee programs, and fostering a remarkable company culture. At our core, we champion values such as transparency, curiosity, respect, and above all, the pursuit of enjoyment.
 
In addition, we offer a range of appealing perks, including:
 
A Professional Development Budget
Dedicated Wellness Days and Wellness Week
A Lifestyle Spending Account
An Employee Recognition Program
 
Join us in shaping the future of our organization, where your talent and dedication can truly thrive. We invite you to apply and become a valuable member of our team!
 
BlueCat is an Equal Opportunity Employer that is committed to inclusion and diversity. We also take affirmative action to offer employment and advancement opportunities to all applicants, including minorities, women, protected veterans, and individuals with disabilities. BlueCat will not discriminate or retaliate against applicants who inquire about, disclose, or discuss their compensation or that of other applicants. 
Apply Now
Apply Now

More jobs like this

15+ more matching roles are waiting

You're seeing the free preview. Unlock the full database to filter every agentic AI role by stack, salary, and country, and get to the new ones before everyone else applies.

Unlock all jobs →

Day pass $4.99 · Lifetime access and daily alerts $29.99

Explore related roles

Get jobs like this in your inbox daily

Be first to apply. Daily alerts are included with lifetime access.