AI Engineer
Manulife Voir toutes les offres
- Toronto, ON
- Permanent
- Temps-plein
- Develop, train, and deploy machine learning models to support contact center optimization and quality automation.
- Build and maintain ML pipelines for data prep, feature engineering, model training, testing, and monitoring.
- Apply MLOps best practices including CI/CD, model versioning, drift detection, and performance monitoring.
- Develop, configure, and test GenAI solutions for contact center workflows including agent assist, summarization, knowledge retrieval, and QA automation.
- Build prompt frameworks and templates for operational use cases.
- Evaluate and compare LLM capabilities across platforms (OpenAI, Azure OpenAI, Anthropic, Google, etc.).
- Conduct iterative experimentation to improve model accuracy, tone, compliance, and consistency.
- Integrate LLMs with enterprise data sources using retrieval-augmented generation (RAG).
- Design evaluation methodologies including grounding tests, hallucination detection, correctness scoring, and safety checks.
- Create scoring rubrics and benchmark datasets tailored to contact center scenarios.
- Run side-by-side model comparisons and maintain dashboards for accuracy, latency, and cost.
- Test solutions against compliance, risk, and privacy guidelines.
- Build prototypes using Python, APIs, vector databases, embeddings, and orchestration frameworks.
- Experience developing and deploying ML models (supervised, unsupervised, deep learning) in production.
- Skilled with ML frameworks such as TensorFlow, PyTorch, scikit-learn.
- Familiarity with MLOps tools (MLflow, Kubeflow, Azure ML).
- Strong understanding of model lifecycle management and monitoring.
- Develop pipelines to prepare transcripts, metadata, and knowledge sources for GenAI.
- Use tools such as Azure OpenAI, LangChain, or Semantic Kernel.
- Partner with engineering to hand off production-ready logic and evaluation artifacts.
- Hands-on experience with custom ML model development
- Strong Python skills (pandas, numpy, scikit-learn, LangChain/Semantic Kernel)
- Understanding of NLP concepts including summarization, classification, and semantic similarity
- Experience with large conversational datasets (voice, chat, digital)
- Familiarity with cloud services (e.g., AWS Bedrock, Connect)
- Hands-on experience with LLMs, prompt design, and evaluation
- Experience implementing RAG systems with vector databases such as Pinecone, Milvus, or ChromaDB.
- Experience working with APIs, embeddings, vector databases, and knowledge bases
- Knowledge of responsible AI, safety evaluation, and compliance testing.
- We’ll empower you to learn and grow the career you want.
- We’ll recognize and support you in a flexible environment where well-being and inclusion are more than just words.
- As part of our global team, we’ll support you in shaping the future you want to see.