AI Engineer

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

📋 Description

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

• Develop and maintain AI functionalities across an enterprise platform.

• Execute agent runtimes, model routing, retrieval-augmented generation (RAG), tool/function invocation, safety measures, evaluation, monitoring, cost management, latency optimization, and quality controls for production.

• Transition AI functionalities from prototypes to monitored production environments.

• Conduct thorough evaluations of AI behavior.

• Collaborate with product and engineering teams to identify suitable applications of AI.

• Transform experiments into valuable, reliable, measurable, safe, and cost-efficient production features.

• Integrate evaluation discipline into the delivery workflow.

• Assist client teams in making informed decisions regarding the value creation of AI.

⛳️ Requirements

• Proven experience in delivering software driven by large language models (LLMs), machine learning models, RAG systems, or agentic workflows to actual production users.

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

• In-depth understanding of RAG, grounding, retrieval quality, prompt design, context management, and evaluation strategies.

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

• Capacity to prioritize cost, latency, reliability, and safety as primary engineering constraints.

• Expertise in constructing guardrails and controls for AI systems, addressing untrusted retrieved content, tool output risks, and failure modes.

• Experience in monitoring production AI behavior and refining systems based on empirical evidence.

• Strong software engineering skills with the ability to collaborate effectively with backend, platform, product, and security teams.

• Excellent communication and collaboration abilities suitable for client-facing consulting scenarios.

• Practical mindset focused on delivering business value and responsible outcomes.

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

• Experience with MCP, application-to-application (A2A), multi-agent orchestration, AI tool invocation, or agent evaluation.

• Knowledge of LLM-as-judge methodologies calibrated against human evaluation.

• Background in semantic knowledge management, ontologies, knowledge graphs, or semantic layers.

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

• Proficiency in using AI-assisted development tools with a strong emphasis on review, testing, and safety protocols.

🏝️ Benefits

• Annual training allowance of $2,000.

• Paid time off.

• Paid holidays.

• Additional benefits.