Back to jobs

Principal Software Engineer - AI

Intuitive.ai
Canada
Full-time
Applications go directly to the hiring team

Full Description

About us:

Intuitive is an innovation-led engineering company delivering business outcomes for 100’s of Enterprises globally. With the reputation of being a Tiger Team & a Trusted Partner of enterprise technology leaders, we help solve the most complex Digital Transformation challenges across following Intuitive Superpowers:

Modernization & Migration

* Application & Database Modernization

* Platform Engineering (IaC/EaC, DevSecOps & SRE)

* Cloud Native Engineering, Migration to Cloud, VMware Exit

* FinOps

Data & AI/ML

* Data (Cloud Native / DataBricks / Snowflake)

* Machine Learning, AI/GenAI

Cybersecurity

* Infrastructure Security

* Application Security

* Data Security

* AI/Model Security

SDx & Digital Workspace (M365, G-suite)

* SDDC, SD-WAN, SDN, NetSec, Wireless/Mobility

* Email, Collaboration, Directory Services, Shared Files Services

Intuitive Services:

* Professional and Advisory Services

* Elastic Engineering Services

* Managed Services

* Talent Acquisition & Platform Resell Services

About the job:

Title: Principal Software Engineer - AI

Start Date: Immediately

# of Positions: 1

Position Type: Full Time/ Contract

Location: Remote across Canada (occasional travel to USA)

About the Role:

We are seeking a hands-on Principal Software Engineer - AI within Digital Technology to lead critical engineering initiatives for the Enterprise Infrastructure AI Platform, with primary ownership across agentic AI experience layers, advanced platform UI, and high-performance platform runtime patterns.

This role requires a deeply technical leader who can operate as both a strategic engineer and an elite builder. The ideal candidate will bring hands-on experience across software engineering, infrastructure, AI, and UI — with strong expertise in Python-based platform engineering and a proven track record building AI agents, agent orchestration systems, and distributed applications. This engineer will help define how the Enterprise Generative AI Platform is experienced by developers, operators, and platform consumers across enterprise-grade chat, workflow, agent, desktop, gateway, observability, and control-plane surfaces.

Key Responsibilities

As a Principal Software Engineer - AI, you will:

* Lead complex technology initiatives across the Enterprise Generative AI Platform with broad organizational impact, driving engineering decisions that shape the platform's experience and runtime layers.

* Design, code, test, debug, and document large-scale platform components across frontend and backend layers — shipping production code daily.

* Architect and build rich product experiences for agent control consoles, workflow builders, runtime dashboards, observability surfaces, and developer self-service experiences.

* Act as a senior technical authority for AI agent frameworks including tool execution orchestration, agent runtime lifecycle management, and human-in-the-loop operational experiences.

* Build scalable backend systems that optimize for latency, throughput, resiliency, and concurrency — including event-driven services, durable workflow orchestration, and agent-to-agent handoff patterns.

* Establish patterns for high-performance Python services including orchestration layers, streaming responses, asynchronous task coordination, and responsive UI interactions.

* Define and drive UI architecture standards for enterprise frontend frameworks, reusable design systems, and interactive control-plane applications.

* Create reusable engineering patterns for agent observability, telemetry-aware UX, runtime tracing views, evaluation reporting, and platform health visualization.

* Mentor senior engineers and lead through design reviews, code reviews, architecture reviews, and direct contribution in the codebase.

* Influence standards around secure software development, performance engineering, test automation, and production readiness.

Required Qualifications

* 7+ years of hands-on Python experience building production services, APIs, and platform tooling — systems engineering, not scripting.

* 5+ years building modern web backends and UI platforms with emphasis on performance, usability, and maintainability.

* 2+ years building event-driven or distributed backend systems — message queues, workflow orchestration engines, durable execution patterns, and service-to-service communication.

* 1-2 years building and operating LLM-powered applications and AI agents in production or advanced prototype environments.

* 1+ year working with agentic AI orchestration frameworks — with the ability to evaluate trade-offs between graph-based, code-first, and declarative agent architectures.

* Experience building multi-step, tool-calling agents — function calling, structured outputs, dynamic tool routing, and agent loops with planning, execution, and self-correction.

* Experience with agent memory — short-term context management, long-term retrieval-augmented generation, and working memory patterns for multi-turn workflows.

* Experience with agent state management — checkpointing, durable execution, state persistence across restarts, and context window optimization.

* Experience with agent observability — execution tracing, step-level debugging, token and cost monitoring, and evaluation of agent quality and task completion.

* Experience with prompt engineering at scale — system prompt design, structured reasoning, prompt versioning, and regression testing across model updates.

* Experience with asynchronous Python services, streaming responses, and high-concurrency design for real-time interactions.

* Experience integrating multiple LLM providers — model routing, fallback strategies, and provider abstraction for cost and quality optimization.

Preferred Qualifications

* Experience with durable workflow orchestration for long-running agent tasks — activity-based execution, retry policies, saga patterns, and agent-to-agent handoffs through workflow engines.

* Experience with event-driven architecture for agent systems — event sourcing, pub/sub messaging, command-query separation, and asynchronous task coordination across agent boundaries.

* Experience with agent recovery and resilience — graceful degradation on model failures, checkpoint-based recovery, and timeout management for non-deterministic execution.

* Experience with agent security — prompt injection defense, output guardrails, sandboxed tool execution, and audit logging for compliance.

* Experience building human-in-the-loop workflows — approval gates, confidence-based routing, and intervention points for agent debugging in production.

* Experience with multi-agent orchestration — supervisor/worker patterns, agent-to-agent communication, shared context, and parallel execution with result aggregation.

* Experience with agent cost engineering — token optimization, semantic caching, and model routing for cost-quality trade-offs at scale.

* Experience building agent evaluation pipelines — regression testing across model updates, drift monitoring, and benchmark-driven quality measurement.

* Experience with multimodal agents — vision-language capabilities, document understanding, and multi-modal tool use.

* Demonstrated pattern of staying current with the rapidly evolving AI agent ecosystem.

What We're Looking For

* You are equally fluent in frontend architecture conversations and Python backend design reviews — and you ship production code in both.

* You think in systems but build in details. You care about API latency and button placement with equal intensity.

* You have built AI agents or orchestration systems and understand the unique challenges of non-deterministic, tool-calling, multi-step workflows.

* You obsess over developer and operator experience — building surfaces that make complex systems feel simple.

* You raise the engineering bar through code, not just commentary. You lead by building.

* You can navigate ambiguity across product, platform, and infrastructure boundaries and drive clarity through execution.

* You mentor by example and create leverage through reusable patterns, not just individual contributions.

Applications go to the hiring team directly