1 day ago
Toronto, CanadaSenior
Responsibilities
- Design, build, and operate ML and GenAI features from data ingestion and feature pipelines through model serving and monitoring.
- Build LLM-powered search, assistant, and agent applications using RAG pipelines, tool integrations, and multi-step workflows.
- Create GenAI evaluation frameworks using offline benchmarks, online metrics, and human review.
- Implement GenAI guardrails, prompt-injection defenses, hallucination mitigation, and responsible AI practices.
- Apply MLOps practices including versioning, automated testing, A/B testing, drift detection, and safe rollbacks.
- Translate product and data science needs into technical requirements and scoped delivery plans.
- Write design documents, participate in design reviews, and provide code reviews.
- Mentor mid-level engineers on production ML practices and system design.
- Optimize model, prompt, and infrastructure choices for latency, cost, and quality.
- Identify and resolve pipeline, serving, and platform performance bottlenecks.
Requirements
- Bachelor's or master's degree in Computer Science, Mathematics, or a related field, or equivalent professional experience.
- At least 5 years of software engineering experience, including at least 3 years building and deploying ML models in production.
- Hands-on experience across the ML lifecycle, including training, evaluation, deployment, monitoring, and retraining.
- Strong Python skills and experience with ML frameworks such as PyTorch, TensorFlow, or scikit-learn.
- Experience with at least one major cloud platform, including AWS, Azure, or Google Cloud, and with distributed workloads.
- Working knowledge of data pipelines, feature engineering, and large-scale data processing.
- Familiarity with experiment tracking, model registries, feature stores, or orchestration frameworks.
- Experience with CI/CD for ML, automated validation, and rollback strategies.
- Experience shipping LLM-based features using prompt engineering, few-shot techniques, and tool or function calling.
- Experience building RAG systems with embeddings, vector databases, and retrieval tuning.
- Exposure to agentic workflows and orchestration frameworks such as LangChain, LlamaIndex, or ADK.
- Understanding of APIs, microservices, reliability fundamentals, data governance, privacy, bias, and explainability in AI systems.
- Clear communication and a collaborative approach with technical and non-technical partners.
- Relevant cloud platform or technology certification is a preferred qualification.
Benefits
- Flexible hybrid work arrangement with no set in-office requirement for employees near an office.
- Innovative work, growth opportunities, caring coworkers, and purpose-driven work.
- Employee resource groups and a stated commitment to diversity, equity, inclusion, and belonging.
- Accessible hiring and assessment accommodations are available for candidates with disabilities.
Tech Stack
Categories
About Benevity
Benevity builds an enterprise SaaS platform for corporate social impact, covering employee giving, volunteering, grants management, ERGs, and donation processing with global charity vetting. Companies use it to run and measure programs for employees and customers, with integrations and payment rails. Founded in 2008 and headquartered in Calgary, it is privately held and part of Hg’s portfolio, serving many large, multinational brands.