GenAI Platform Engineer – Production AI & LLMOps

Compunnel Inc.; Montreal; On-site; CAD 100,000 - 140,000; Full time

Job summary

Compunnel, Inc. is looking for two experienced Applied AI Engineers in Montreal. The role involves designing and building an enterprise-grade GenAI workflow platform to enhance data extraction and automate workflows.

The ideal candidates should have strong front-to-back engineering experience, practical application of GenAI solutions, and proven abilities in architecting GenAI systems. The position requires in-office presence three times weekly and offers competitive remuneration.

Qualifications

• 5+ years of strong front-to-back engineering experience (Python or Java).
• Practical application of GenAI solutions in an enterprise environment.
• Experience with GenAI orchestration in production.
• Building and operating production grade GenAI / LLM platforms.
• Expertise in LLMOps including evaluation harnesses and reliability measurement.

Responsibilities

• Design reusable GenAI workflows for Lending business lines.
• Develop AI-based document ingestion and data extraction capabilities.
• Build AI-powered assistants for Lending systems.
• Deliver automated content generation workflows.
• Provide expert GenAI architecture advice.
• Establish LLMOps practices and audit monitoring.
• Design controls for PII handling in regulated environments.

Skills

Front-to-back engineering (Python or Java)

AI/ML platforms experience

GenAI solutions application

GenAI orchestration frameworks

Production grade GenAI/LLM platforms

LLMOps expertise

AI-first data ingestion pipelines

Advanced retrieval techniques

Evaluation metrics understanding

Experience with production failures

Job description

JOB SUMMARY
Client Fixed Income Institutional Lending Technology team is seeking two highly experienced Applied AI Engineers to design, build, and operate an enterprise-grade GenAI workflow platform. This platform will enhance document data extraction, embed productivity assistants, and automate business workflows across various business lines. This is a hands-on role focused on production systems, not research or demos, requiring deep understanding of GenAI failure modes, evaluation, and governance. The engineers will contribute to reusable GenAI workflows, develop robust AI-based document ingestion and data extraction capabilities with human-in-the-loop review, build agentic AI-powered assistants, and deliver automated content generation. They will also provide expert architectural advice on GenAI, establish LLMOps practices, and implement controls for data handling in a regulated environment, with a clear path to platform ownership and defining shared GenAI standards.

Key Responsibilities
• Design and evolve reusable GenAI workflows used across Lending business lines.
• Develop an enterprise grade AI-based document ingestion and data extraction capability, including traceability, confidence scoring, and human-in-the-loop review.
• Build AI-powered assistants embedded in Lending systems using agentic workflows.
• Deliver automated content and deck generation workflows for reporting and approvals.
• Provide expert advice on GenAI architecture including model selection, orchestration patterns, and evaluation strategy.
• Establish LLMOps practices: extraction accuracy, assistant reliability, prompts management, and audit monitoring.
• Design and implement controls for entitlements, PII handling within open-source models in a regulated environment.

Required Qualifications
• 5+ years of strong front-to-back engineering experience (Python or Java), focusing on AI ML platforms and workflows.
• Recent dedicated experience in practical application of GenAI solutions in an enterprise environment.
• Designing and operating GenAI orchestration frameworks in production (e.g., LangChain systems), beyond vendor examples.
• Proven experience building and operating production grade GenAI / LLM platforms, applying patterns such as RAG, tool/function calling, agentic workflows, and validated structured outputs.
• Strong LLMOps expertise, including evaluation harnesses, prompt and version management, regression testing, observability, and reliability measurement in production systems.
• Hands on experience building AI-first data ingestion pipelines with measurable quality, accuracy, and reliability.
• Advanced retrieval experience, including advanced vector search, multi vector and late interaction approaches (e.g., ColBERT, chunking), multi stage retrieval pipelines, metadata filtering, re ranking.
• Solid understanding of evaluation metrics (e.g., recall vs precision, latency vs quality, MRR, NDCG) and how they shape practical RAG system design.
• Experience operating GenAI systems through real production failures (model regressions, retrieval degradation, prompt drift, data quality issues) and designing mitigation strategies.
• Day 1 onboarding onsite / in-office presence required 3x/week in Montreal.

Preferred Qualifications
• Fixed Income or Institutional Lending domain experience.
• Experience working in regulated environments with strong audit and control requirements.
• Familiarity with enterprise security, data governance, and entitlement models.
• Experience designing reusable internal platforms or shared developer tooling.
• Frontend experience (Angular or React).