Gen AI Engineer (Python,RAG, LangChain, LangSmith)
- Montreal, QC, Canada
Full-time
Applications open in a new tab.
Job details
- Job type
- Full-time
- Apply by
- Posting language
- English
- Posted
Original job description
The Role: GEN AI Engineer (Python,RAG, LangChain, LangSmith)
We are looking for a Senior AI/ML Engineer with expertise in Retrieval-Augmented Generation (RAG), vector databases, multimodal AI, and prompt engineering. The candidate will be responsible for building intelligent AI applications that leverage structured and unstructured enterprise data.
Key Responsibilities
- Design and implement enterprise-scale RAG pipelines.
- Build and optimize semantic search solutions using vector databases.
- Develop multimodal AI applications capable of processing text, images, documents, and other data formats.
- Create and optimize prompts for improved LLM performance and accuracy.
- Develop data ingestion, chunking, embedding, retrieval, and ranking strategies.
- Evaluate and improve AI solution quality, accuracy, and latency.
- Collaborate with cross-functional teams to integrate AI capabilities into enterprise applications.
Required Skills
- Strong proficiency in Python.
- Hands-on experience building RAG solutions.
- Experience with vector databases such as Pinecone, Weaviate, Milvus, Chroma, or OpenSearch.
- Strong understanding of embeddings, retrieval strategies, and semantic search.
- Expertise in Prompt Engineering.
- Experience building Multimodal AI solutions.
- Knowledge of LLMs and foundation models.
- Experience with Amazon Bedrock and AWS AI services.
- Familiarity with LangChain for RAG implementations.
- Knowledge of evaluation frameworks and AI observability tools.
- Experience deploying AI/ML applications in production environments.
Nice to Have
- Knowledge of Agentic AI concepts.
- Experience with LangGraph or multi-agent architectures.
- Exposure to MLOps and model deployment pipelines.
More about this job
Responsibilities
Design and build enterprise-scale RAG pipelines, semantic search solutions, and multimodal AI applications using enterprise data. Improve prompts, ingestion and retrieval strategies, and solution quality, accuracy, and latency while collaborating with teams to integrate AI into enterprise applications.
Requirements
Requires strong Python skills and hands-on experience with RAG, vector databases, embeddings, semantic search, prompt engineering, multimodal AI, and LLMs. Candidates should also have experience with Amazon Bedrock or AWS AI services, LangChain, AI evaluation and observability, and production deployments; agentic AI, LangGraph, and MLOps are advantageous.
Skills
- Python
- Retrieval-Augmented Generation (RAG)
- Vector Databases
- Multimodal AI
- Prompt Engineering
- Embeddings
- Semantic Search
- Amazon Bedrock
- AWS AI Services
- LangChain
- AI Evaluation
- AI Observability
- Production AI/ML Deployment
- Agentic AI
- LangGraph
- MLOps
Visa sponsorship
Not detected in the job text
Categories
- Technology
- Software
- Data & Analytics
- Engineering
Keywords
- Python
- Retrieval-Augmented Generation (RAG)
- Vector Databases
- Pinecone
- Weaviate
- Milvus
- Chroma
- OpenSearch
- Embeddings
- Retrieval Strategies
- Semantic Search
- Prompt Engineering
- Multimodal AI
- Large Language Models (LLMs)
- Foundation Models
- Amazon Bedrock
- AWS AI Services
- LangChain
- LangSmith
- AI Evaluation Frameworks
- AI Observability
- Production Deployment
- Agentic AI
- LangGraph
- Multi-Agent Architectures
- MLOps
- Data Ingestion
- Chunking
- Ranking Strategies