Senior Gen AI Engineer (LLMs, RAG)
Share
Job Location:
Monthly Salary:
Posted on:
14 hours ago
Vacancies:
1 Vacancy
Job Summary
Senior Gen AI Engineer (LLMs RAG)
Build next-generation AI solutions in the insurance industry using LLMs RAG pipelines vector databases and Azure cloud. This hybrid Toronto role focuses on designing scalable GenAI systems deploying production-ready AI services and partnering with engineering and business teams to transform complex data into intelligent advisor tools.
What is in it for you:
Salaried: $50-60 per hour.
Incorporated Business Rate: $60-70 per hour.
8-month contract with the potential for permanent employment.
Full-time position: 37.50 hours per week.
Remote on Monday and Friday; on-site Tuesday to Thursday.
Responsibilities:
Architect and develop LLM-based solutions including retrieval-augmented generation (RAG) pipelines embeddings model fine-tuning and evaluation frameworks.
Build scalable Generative AI microservices and integrate them with internal enterprise systems.
Perform advanced prompt engineering agent design and implement safety guardrails for AI systems.
Evaluate open-source and commercial language models based on performance cost and risk.
Collaborate with data teams to prepare training datasets knowledge bases and analytics pipelines.
Manage ingestion and refresh processes for knowledge bases supporting RAG architectures.
Implement monitoring and feedback loops to continuously improve model performance and solution quality.
Partner with business stakeholders to define problem statements data requirements and delivery approaches.
Document solution architecture data sources and development standards.
Present model performance insights and business impact to senior stakeholders.
Contribute to business cases and support change-management considerations for solution adoption.
Create architecture diagrams and technical documentation for engineering teams.
Track tasks and progress using Jira in an agile project environment.
Collaborate with cross-functional teams including data infrastructure backend and frontend engineering.
Mentor junior team members and promote AI engineering best practices.
Ensure compliance with enterprise security standards and insurance regulatory requirements.
What you will need to succeed:
Bachelors degree in Computer Science Mathematics Engineering or equivalent practical experience.
6 years of experience in machine learning natural language processing or AI engineering.
2 years of experience working with Generative AI and large language models.
Hands-on experience with LLM platforms such as OpenAI Azure OpenAI Anthropic or Llama.
Strong expertise in retrieval-augmented generation (RAG) vector databases embeddings and model evaluation methods.
Proficiency in Python and experience building data pipelines.
Experience designing and deploying cloud-native architectures preferably on Microsoft Azure.
Proven experience deploying Generative AI solutions in production environments with monitoring and operational controls.
Strong SQL and data modeling skills.
Familiarity with relational and NoSQL databases or distributed data environments.
Familiarity with BI or visualization tools such as Power BI or Tableau is considered an asset.
Knowledge of classical machine learning or statistical methods such as regression clustering or tree-based models.
Ability to translate technical findings into business insights and communicate with non-technical stakeholders.
Strong problem-solving collaboration and communication skills.
Experience in insurance financial services or regulated industries is considered an asset.
Why Recruit Action
Recruit Action (agency permit: AP-2504511) provides recruitment services through quality support and a personalized approach. As part of the screening process some applications may be reviewed using artificial intelligence tools. Only candidates who meet the hiring criteria will be contacted.
# MFCJP
Required Skills:
