Senior Platform / Software Engineer - AI

About us:

Intuitive.AI is one of the fastest-growing (INC 5000, CRN) Cloud & SDx solution and services companies supporting enterprise customers on a global scale. Intuitive is an "Engineering Company" delivering measurable value and key business outcomes.

Intuitive Superpowers:

- DataOps & AI/ML

- Cloud Native, AppSecOps, DevSecOps

- Cloud Migration & Transformation

- Cloud FinOps

- Cybersecurity (App/Data/Infra) & GRC

- SDx & Digital Workspace

We are proud to partner with some of the world's leading enterprises and serve 200+ customers across different industry verticals. We have achieved many milestones along the way, including being recognized as a top-10 fast-growth 150 IT company in the Americas by CRN in 2022 and being named one of America's fastest-growing private companies by INC 5000 in 2022. That’s not all! Even CIO Review awarded us as the Most Promising Cloud Migration Company and Artificial Intelligence Solutions Provider in 2022.

Job Description:

Title: Senior Platform / Software Engineer - AI

Position Type: Full Time

Location: Remote across Canada

About the Role

We're looking for a hands-on Senior Full-Stack AI Engineer to build and operate an enterprise platform that combines data from many independent sources, presents operational insights through a dashboard application, and enables users to complete work through AI agents.

This is an engineering role first. You will design and ship production capabilities across data integrations, backend APIs, web experiences, and agent workflows. You will also bring strong quality-engineering discipline to the team by building automated coverage, AI evaluations, and release gates alongside the features you deliver.

The expected balance is approximately 70% product and platform engineering and 30% quality engineering and

evaluation. Quality is not a separate testing phase: it is part of how you design, implement, observe, and operate software in production.

The ideal candidate is comfortable moving through the full stack, understands how modern AI agents are built, and knows when to apply unit, contract, integration, end-to-end, exploratory, performance, security, and user acceptance testing.

Key Responsibilities

Full-Stack AI Engineering

• Build production AI agents with planning, multi-step tool use, structured outputs, state management, error recovery, and human-in-the-loop controls.
• Develop agent runtime capabilities including lifecycle management, retries, resumability, timeouts, fallback behavior, checkpointing, and durable execution.
• Design secure tool integrations with clear schemas, validated inputs and outputs, authorization boundaries, audit trails, and safe handling of external systems.
• Engineer context, retrieval, and memory across prompts, conversation state, tool results, RAG pipelines, short-term working memory, and persistent memory.
• Build backend services and APIs in Python or TypeScript for agent execution, data access, workflow orchestration, evaluation, and application features.
• Build responsive dashboard experiences using modern frontend technologies such as React and TypeScript, including operational workflows, drilldowns, visualizations, approvals, and agent activity views.
• Integrate data from multiple source systems through APIs, databases, scheduled synchronization, event-driven workflows, and background processing.
• Build AI-powered platform workflows that interact safely with cloud and infrastructure services using validated tool contracts, least-privilege access, approval gates, audit trails, idempotent operations, and recoverable failure handling.
• Design for production operations with authentication, role-based access control, observability, performance, resilience, and secure handling of enterprise data.
• Instrument applications and agents with logs, metrics, distributed traces, token and cost monitoring, latency budgets, and step-level decision visibility.
• Participate in architecture reviews, code reviews, incident response, production support, and continuous improvement of engineering standards.

Quality Engineering & Evaluation

• Apply a risk-based test strategy covering unit, component, contract, integration, system, end-to-end, regression, exploratory, performance, security, and user acceptance testing.
• Build automated tests for backend APIs, dashboard workflows, authentication, authorization, databases, data integrations, background jobs, and asynchronous workflows.
• Validate data across source systems, integrations, APIs, databases, dashboard visualizations, and agent context using schema checks, reconciliation, freshness, completeness, uniqueness, and transformation rules.
• Build AI evaluation pipelines using benchmark datasets, deterministic checks, rubric-based scoring, repeated trials, model-based evaluation, and human review.
• Evaluate agent behavior for task completion, groundedness, relevance, consistency, tool selection, tool-input accuracy, safety, latency, and failure handling.
• Test failure scenarios including stale or conflicting data, malformed payloads, unavailable dependencies, invalid tool responses, timeouts, partial failures, prompt injection, data leakage, unauthorized actions, and runaway loops.
• Integrate automated tests and AI evaluations into pull-request checks, deployment gates, post-deployment verification, and scheduled regression cycles.
• Use production incidents and escaped defects to create durable regression tests, evaluation cases, and engineering improvements.
• Work with product and business stakeholders to define acceptance criteria and support UAT with realistic scenarios, environments, test data, and traceable evidence.

Required Qualifications

• 5+ years of software engineering experience building and operating production web applications, backend services, distributed systems, or data-intensive platforms.
• Hands-on production experience building LLM-powered applications, AI agents, RAG systems, or tool-calling workflows.
• Strong Python or TypeScript skills for application development, backend services, agent orchestration, test automation, and evaluation tooling.
• Experience building modern web applications and APIs, with practical knowledge of frontend, backend, database, and integration concerns.
• Experience building multi-step agents with tool orchestration, state management, retries, failure recovery, and human approval points.
• Practical understanding of context engineering, prompt design, retrieval, session state, memory, observability, and agent-specific failure modes.
• Experience integrating multiple data sources through APIs, databases, scheduled jobs, events, or background workflows.
• Hands-on experience building or integrating software with public-cloud platform services in AWS, Azure, or GCP, including infrastructure lifecycle workflows, platform APIs, identity and access controls, asynchronous operations, observability, and failure recovery.
• Understanding of platform and infrastructure concepts including compute, containers, networking, storage, secrets, quotas, auditability, idempotency, and infrastructure automation.
• Strong SQL and data-validation skills, including tracing and reconciling data across source systems and application layers.
• Strong understanding of unit, component, contract, integration, system, end-to-end, regression, exploratory, performance, security, and user acceptance testing.
• Hands-on experience with automated testing frameworks such as pytest, Playwright, Cypress, or equivalent tools.
• Experience testing non-deterministic AI behavior using evaluation datasets, behavioral criteria, quality thresholds, and trace-based diagnostics rather than exact-text matching alone.
• Experience integrating automated tests and quality gates into Git-based CI/CD pipelines.
• Ability to diagnose production issues using logs, metrics, traces, database queries, API responses, model inputs and outputs, and agent execution history.

Preferred Qualifications

• Experience with FastAPI, React, PostgreSQL, vector databases, workers, schedulers, workflow engines, or event-driven architectures.
• Experience with private-cloud and virtualization platforms such as VMware, OpenStack, or equivalent enterprise infrastructure environments.
• Experience with an agent framework such as Pydantic AI, LangChain/LangGraph, OpenAI Agents SDK, Google ADK, Vercel AI SDK, Mastra, or equivalent.
• Experience with AI observability or evaluation platforms such as LangSmith, Langfuse, OpenTelemetry GenAI conventions, or equivalent tooling.
• Experience with data-quality and contract-testing tools or patterns such as Great Expectations, dbt tests, Soda, Pact, schema registries, or equivalent approaches.
• Experience with Kubernetes, containers, Terraform or equivalent infrastructure-as-code tooling, microservices, and infrastructure or operations tooling.
• Experience testing enterprise authentication, authorization, secrets handling, audit logging, and secure tool execution.
• Experience with performance testing tools such as k6, Locust, or JMeter.
• Familiarity with multi-agent orchestration, supervisor/worker patterns, agent-to-agent communication, and human-in-the-loop workflows.
• Track record of mentoring engineers or leading technical design across ambiguous product and platform boundaries.

What We're Looking For

• You are a full-stack AI engineer who treats quality as part of engineering ownership, not work handed to another team after implementation.
• You can build an agent, the APIs and user experience around it, and the automated evidence needed to trust it in production.
• You can reason across source data, integrations, backend services, dashboard behavior, and agent execution to find where failures originate.
• You understand both deterministic software testing and the additional evaluation techniques required for non-deterministic AI systems.
• You know when to use unit, integration, contract, end-to-end, exploratory, performance, security, or UAT approaches and can explain the trade-offs.
• You make practical decisions about delivery speed, test depth, operational risk, and release confidence.
• You communicate clearly across engineering, product, data, operations, and business stakeholders