AI Systems Engineer

Meet Benevity

Benevity is the way the world does good, providing companies (and their employees) with technology to take social action on the issues they care about. Through giving, volunteering, grantmaking, employee resource groups and micro-actions, we help most of the Fortune 100 brands build better cultures and use their power for good. We’re also one of the first B Corporations in Canada, meaning we’re as committed to purpose as we are to profits. We have people working all over the world, including Canada, Spain, Switzerland, the United Kingdom, the United States and more!

We’re looking for an AI Systems Engineer to help build and optimize real-world applications powered by large language models and intelligent automation. In this role, you’ll contribute to the design and deployment of AI features that integrate retrieval systems, agents, and foundation models into production-grade systems. You’ll work cross-functionally with data scientists, product managers, and platform engineers to deploy, optimize, and maintain reliable and scalable ML/AI services in a production environment—ensuring they perform well and deliver value to all our clients.

What you’ll do:

AI System Development & Implementation

• Develop and maintain AI-powered workflows using LLMs, embeddings, and automation tools
• Contribute to building RAG (retrieval-augmented generation) systems integrated with platform features
• Build and improve natural language interfaces such as semantic search and text-to-SQL queries
• Assist with prompt engineering, evaluation, and fine-tuning of LLMs for production use

Collaborate in the design of scalable, modular AI components that can be reused across products

Platform Engineering & Integration

• Deploy AI services in cloud-native environments (AWS, GCP, or Azure) using containerized pipelines
• Build and monitor embedding and vector database workflows (e.g., FAISS, Pinecone, Weaviate)
• Maintain CI/CD workflows and support versioning, testing, and safe deployment of AI systems
• Contribute to LLMOps efforts around logging, observability, and responsible AI practices

Work with data teams to ensure clean, structured inputs for model training and inference

Collaboration & Technical Growth

• Work cross-functionally with product, design, and data science to bring AI features to life
• Participate in architectural discussions and advocate for scalable, maintainable solutions
• Stay up to date with advancements in the LLM and MLOps ecosystem and explore new tools and frameworks
• Contribute to documentation and internal tooling that improve team efficiency and transparency

What you’ll bring:

• A Bachelor's degree in Computer Science, Engineering, or related field (or equivalent experience)
• 3+ years of software engineering experience, with at least 1–2 years working with ML/AI systems
• Solid Python development skills, including building APIs or backend services with FastAPI or Flask
• Experience integrating with LLMs (e.g., OpenAI, Cohere) and using embedding models
• Familiarity with retrieval systems and vector databases (Pinecone, FAISS, Qdrant, etc.)
• Hands-on experience with cloud platforms and containerized deployment (e.g., Docker, Kubernetes)
• Understanding of prompt engineering, semantic search, and NLP tasks like text classification or Q&A
• Interest in responsible AI practices and building traceable, explainable ML pipelines
• Exposure to tools such as LangChain, MLflow, LangSmith, or Weights & Biases is a plus

Technical Skills & Expertise:

• Programming: Proficient in Python; experience with backend development and REST APIs
• AI Tools: Familiar with Hugging Face, OpenAI APIs, LangChain, and RAG pipelines
• Infrastructure: Comfortable with cloud deployment (AWS preferred), Docker, Kubernetes
• Vector Search: Experience with embeddings and vector databases like FAISS or Pinecone
• MLOps/LLMOps: Exposure to tools like MLflow, BentoML, or LangSmith
• Data Systems: Familiar with SQL and NoSQL databases, data pipelines, and structured data integration
• Monitoring: Experience with observability tools like Datadog, Prometheus, or OpenTelemetry
• Development Practices: Git, CI/CD, agile teamwork, and documentation habits

Discover your purpose at work

We’re not employees, we’re Benevity-ites. From all locations, backgrounds and walks of life, who deserve more …

Innovative work. Growth opportunities. Caring co-workers. And a chance to do work that fills us with a sense of purpose.

If the idea of working on tech that helps people do good in the world lights you up ... If you want a career where you’re valued for who you are and challenged to see who you can become …

It’s time to join Benevity. We’re so excited to meet you.

Where we work

At Benevity, we embrace a flexible hybrid approach to where we work that empowers our people in a way that supports great work, strong relationships, and personal well-being. For those located near one of our offices, while there’s no set requirement for in-office time, we do value the moments when coming together in person helps us build connection and collaboration. Whether it’s for onboarding, project work, or a chance to align and bond as a team, we trust our people to make thoughtful decisions about when showing up in person matters most.

Join a company where DEIB isn’t a buzzword

Diversity, equity, inclusion and belonging are part of Benevity’s DNA. You’ll see the impact of our massive investment in DEIB daily — from our well-supported employee resources groups to the exceptional diversity on our leadership and tech teams.

We know that diverse backgrounds, experiences, skills and passions are what move our business and our people forward, so we're committed to creating a culture of belonging with equal opportunities for everyone to shine. 

That starts with a fair and accessible hiring process. If you want to feel seen, heard and celebrated, you belong at Benevity.

Candidates with disabilities who may require accommodations throughout the hiring or assessment process are encouraged to reach out to accommodations@benevity.com.