About the role
Job Description
Job Title: Senior LLM Engineer
Job Type: Full-time
Location: Canada (Remote)
Experience: 4-6+ Years of Relevant Experience
Job Summary:
Join our team as a Senior LLM Engineer and play a pivotal role in designing, building, and optimizing next-generation Generative AI applications. You will leverage your expertise in Large Language Models, state-of-the-art AI platforms, and cloud technologies to deliver scalable, production-grade AI solutions. We value clear, impactful written and verbal communication as much as deep technical skill.
Responsibilities:
- Lead the architecture and implementation of GenAI systems — including RAG, multi-agent workflows, and autonomous reasoning frameworks.
- Architect and optimize complex data ingestion, embedding, and retrieval pipelines using vector databases.
- Build scalable, low-latency APIs and integrate LLM capabilities into production-grade platforms.
- Evaluate and select appropriate frameworks and tools (e.g., Neo4j vs. Neptune for graph data) based on project needs.
- Mentor junior engineers and drive best practices in system design and deployment.
- Oversee deployment architectures on AWS or Azure, ensuring reliability and cost efficiency.
- Innovate in emerging GenAI areas — multi-agent coordination, MCP, and agent-to-agent communication (A2A).
- Collaborate with leadership and cross-functional teams to align technical roadmaps with strategic goals.
Must-have Skills:
- Python : Expert. Strong design, debugging, and optimization capabilities.
- API Development : Advanced knowledge of FastAPI or equivalent frameworks.
- GenAI Stack : LangChain, LangGraph, LangSmith, and hands-on with multiple LLMs.
- RAG Expertise : End-to-end lifecycle mastery — from data processing to deployment.
- Architectural Thinking : Tool comparison, scalability, fault tolerance, performance trade-offs.
- Cloud/DevOps : Deep hands-on experience with AWS or Azure (infrastructure, monitoring, CI/CD).
Good-to-have Skills:
- Emerging Tech : MCP, A2A agents, advanced orchestration frameworks.
- Responsible AI : Experience applying governance and safety frameworks.
- Leadership : Mentorship, technical roadmap ownership, code review.
- Cross-System Integration : Familiarity with microservices, event-driven design, and messaging queues.
About the role
Job Description
Job Title: Senior LLM Engineer
Job Type: Full-time
Location: Canada (Remote)
Experience: 4-6+ Years of Relevant Experience
Job Summary:
Join our team as a Senior LLM Engineer and play a pivotal role in designing, building, and optimizing next-generation Generative AI applications. You will leverage your expertise in Large Language Models, state-of-the-art AI platforms, and cloud technologies to deliver scalable, production-grade AI solutions. We value clear, impactful written and verbal communication as much as deep technical skill.
Responsibilities:
- Lead the architecture and implementation of GenAI systems — including RAG, multi-agent workflows, and autonomous reasoning frameworks.
- Architect and optimize complex data ingestion, embedding, and retrieval pipelines using vector databases.
- Build scalable, low-latency APIs and integrate LLM capabilities into production-grade platforms.
- Evaluate and select appropriate frameworks and tools (e.g., Neo4j vs. Neptune for graph data) based on project needs.
- Mentor junior engineers and drive best practices in system design and deployment.
- Oversee deployment architectures on AWS or Azure, ensuring reliability and cost efficiency.
- Innovate in emerging GenAI areas — multi-agent coordination, MCP, and agent-to-agent communication (A2A).
- Collaborate with leadership and cross-functional teams to align technical roadmaps with strategic goals.
Must-have Skills:
- Python : Expert. Strong design, debugging, and optimization capabilities.
- API Development : Advanced knowledge of FastAPI or equivalent frameworks.
- GenAI Stack : LangChain, LangGraph, LangSmith, and hands-on with multiple LLMs.
- RAG Expertise : End-to-end lifecycle mastery — from data processing to deployment.
- Architectural Thinking : Tool comparison, scalability, fault tolerance, performance trade-offs.
- Cloud/DevOps : Deep hands-on experience with AWS or Azure (infrastructure, monitoring, CI/CD).
Good-to-have Skills:
- Emerging Tech : MCP, A2A agents, advanced orchestration frameworks.
- Responsible AI : Experience applying governance and safety frameworks.
- Leadership : Mentorship, technical roadmap ownership, code review.
- Cross-System Integration : Familiarity with microservices, event-driven design, and messaging queues.