GenAI Engineer
- Toronto, ON, Canada
Contract
Applications open in a new tab.
Job details
- Job type
- Contract
- Apply by
- Posting language
- English
- Posted
Original job description
GenAI Engineer
Contract – 6+ months
Location –Toronto, ON (Hybrid - 3 days a week onsite)
Overall Experience - 7+ years
AI Experience - 3+ years
*****Looking explicitly for GenAI development experience. Data Science/ML experience will not counted. ******
Key Responsibilities
- Design, develop, and deploy Generative AI applications using LLMs and modern AI frameworks.
- Build RAG pipelines using embeddings, vector databases, semantic search, document chunking, and reranking.
- Develop LLM-powered workflows using frameworks such as LangChain, LangGraph, LlamaIndex, or Semantic Kernel.
- Implement prompt engineering, context management, function calling, and tool integration.
- Integrate GenAI solutions with REST APIs, backend services, and enterprise systems.
- Evaluate model outputs, improve response quality, and implement measures to reduce hallucinations.
- Optimize AI applications for performance, scalability, reliability, and production deployment.
Required Skills
- Strong programming experience in Python and API integration.
- Hands-on experience with Generative AI, LLMs, and RAG-based applications.
- Knowledge of embeddings, vector databases, semantic search, and information retrieval.
- Experience with at least one framework: LangChain, LangGraph, LlamaIndex, or Semantic Kernel.
- Understanding of prompt engineering, context engineering, and LLM orchestration.
- Experience integrating LLMs with backend applications and external tools.
- Familiarity with at least one cloud AI platform, such as Azure OpenAI, Amazon Bedrock, or Google Vertex AI.
Preferred Qualifications
- Experience developing AI agents or agentic AI workflows.
- Knowledge of LLM evaluation, tracing, observability, and hallucination mitigation.
- Experience deploying and monitoring GenAI applications in production.
- Familiarity with hybrid search, reranking, structured outputs, and inference optimization.
More about this job
Responsibilities
Design, develop, and deploy Generative AI applications and RAG pipelines using LLMs, modern frameworks, embeddings, vector databases, and search techniques. Integrate LLM workflows with APIs, backend services, and enterprise systems, while evaluating and improving output quality, reducing hallucinations, and optimizing production performance and reliability.
Requirements
Requires 7+ years of overall experience, including 3+ years of hands-on Generative AI development; data science or general machine learning experience does not count toward the AI experience requirement. Candidates need strong Python and API integration skills, practical experience with LLMs and RAG, familiarity with at least one listed LLM framework and cloud AI platform, and knowledge of prompt engineering and orchestration.
Skills
- Python
- Generative AI
- Large Language Models
- Retrieval-Augmented Generation
- Embeddings
- Vector Databases
- Semantic Search
- LangChain
- LangGraph
- LlamaIndex
- Semantic Kernel
- Prompt Engineering
- API Integration
- LLM Orchestration
- Cloud AI Platforms
- AI Agents
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Software
- Data & Analytics
- Engineering
Keywords
- Generative AI
- Large Language Models
- Retrieval-Augmented Generation
- Python
- LangChain
- LangGraph
- LlamaIndex
- Semantic Kernel
- Embeddings
- Vector Databases
- Semantic Search
- Document Chunking
- Reranking
- Prompt Engineering
- Context Engineering
- Function Calling
- LLM Orchestration
- REST APIs
- Azure OpenAI
- Amazon Bedrock
- Google Vertex AI
- AI Agents
- LLM Evaluation
- Observability
- Hallucination Mitigation
- Hybrid Search
- Structured Outputs
- Inference Optimization
- Production Deployment
- Toronto