Experience: 8+ years

Role Summary

- Lead the development and delivery of enterprise GenAI products, pilots, and scalable AI solutions.
- Architect LLM pipelines, Agentic AI workflows, MCP, Graph RAG, and prompt-based applications.
- Build cloud-native AI solutions using AWS and optimize production performance.
- Collaborate with product, data science, and business teams to deliver AI solutions.
- Drive technical strategy, Agile delivery, DevSecOps, governance, and production reliability.

Required Skills

- 10+ years of engineering experience, including 1-2 years leading AI initiatives.
- GenAI/LLMs: GPT, Claude, Gemini, LLaMA, prompt engineering, fine-tuning.
- AI Frameworks: LangChain, LlamaIndex, Amazon Bedrock, Agentic AI, MCP, Graph RAG.
- Databases & Orchestration: Weaviate, Milvus, PGVector, Neo4j, Neptune, Apache Airflow.
- AWS & DevOps: EKS, Fargate, Lambda, EC2, ELB/NLB, Glue, Athena, Lake Formation, Terraform, Docker, Puppet.
- Robust SDLC, DevSecOps, Agile, system design, and production support experience.

📌 Gen AI Engineer (Toronto)
🏢 apptoza
📍 Toronto