AI Engineer

This is a fully remote position, open to applicants in Canada.

📋 Description

• Assist an external software development organization as a key member of Inviso’s delivery team.

• Design and manage AI capabilities within an enterprise platform.

• Create agent runtimes, model routing, RAG, tool/function invocation, guardrails, evaluation, monitoring, cost management, latency optimization, and production quality controls.

• Transition AI systems from prototype stages to monitored production environments.

• Rigorously assess AI behavior.

• Collaborate with product and engineering teams to ascertain the appropriateness of AI applications.

• Convert experiments into production-ready features.

• Integrate evaluation discipline into the delivery process.

• Assist client teams in making informed choices regarding where AI can deliver genuine value.

⛳️ Requirements

• Proven experience delivering software powered by LLMs, ML models, RAG systems, or agentic workflows to actual production users.

• Background in designing or implementing agent runtime, orchestration, model routing, tool/function invocation, or AI workflow patterns.

• Deep knowledge of RAG, grounding, retrieval quality, prompt design, context management, and evaluation methodologies.

• Experience in constructing evaluation harnesses, golden sets, regression checks, quality gates, or measurable AI performance frameworks.

• Capability to treat cost, latency, reliability, and safety as primary engineering constraints.

• Experience in establishing guardrails and controls for AI systems, particularly concerning untrusted retrieved content, tool output risks, and failure modes.

• Familiarity with monitoring production AI behavior and enhancing systems based on empirical evidence.

• Strong software engineering expertise.

• Ability to work collaboratively with backend, platform, product, and security teams.

• Excellent communication and collaboration skills suited for client-facing consulting roles.

• Pragmatic mindset with the ability to prioritize business value and deploy useful AI capabilities promptly and responsibly.

• Experience with Claude, GPT, Azure OpenAI, open-source models, model routing, fine-tuning, distillation, or small/edge models.

• Familiarity with MCP, A2A, multi-agent orchestration, AI tool invocation, or agent evaluation.

• Experience with LLM-as-judge methodologies calibrated against human evaluation.

• Knowledge of semantic knowledge management, ontologies, knowledge graphs, or semantic layers.

• Familiarity with AI development lifecycle practices encompassing data, build, evaluation, deployment, monitoring, and ongoing improvement.

• Experience utilizing AI-assisted development tools while upholding strong review, testing, and safety protocols.

🏝️ Benefits

• Annual training allowance of $2,000.

• Paid time off.

• Paid holidays.

• Additional benefits.