We are hiring a Senior AI Data Engineer for a Vancouver-based client building an AI/data platform with heavy external data ingestion, non-standard data engineering, and retrieval-driven workflows. This role is best suited for someone who has already worked on production AI/LLM-related data systems, especially where data ingestion, parsing, indexing, retrieval, and backend services come together. * This is not a classic BI / reporting / data warehouse role. * This is not a pure backend API role. * We need someone strong at the intersection of data engineering, AI retrieval / RAG workflows, Python backend services, cloud infrastructure, and messy real-world data pipelines.
What You’ll Do: * Build and maintain data ingestion pipelines for structured and unstructured external data. * Design and support retrieval pipelines for AI/LLM workflows. * Develop Python services and APIs for data processing and retrieval, primarily with FastAPI. * Work with vector-based retrieval, metadata enrichment, chunking, indexing, and synchronization. * Support data flows across Postgres, object storage, vector search, and related stores. * Improve reliability, observability, performance, and maintainability of the existing platform. * Collaborate with software engineers and AI-focused teammates to stabilize and evolve the system. * Contribute to technical design decisions in a fast-changing startup environment.
Requirements: * 5+ years of commercial software/data engineering experience. * Strong commercial experience with Python. * Hands-on commercial experience building data pipelines / ingestion workflows. * Hands-on commercial experience with AI/LLM-related retrieval systems, such as RAG pipelines, vecto search / embedding-based retrieval, or document ingestion / parsing / chunking / indexing workflows. * Experience building or maintaining FastAPI or similar Python backend services. * Experience with AWS data / cloud infrastructure. * Experience with unstructured or semi-structured data. * Strong SQL and practical data modeling skills. * Ability to work independently in ambiguous product environments. * Strong written and spoken English — all technical documentation and client reviews are in English.
Strongly preferred * Production experience with one or more vector databases / vector search technologies, such as Pinecone, pgvector, Qdrant, Weaviate, OpenSearch / Elasticsearch vector search, or FAISS. * Experience with graph databases or connected-data modeling, such as Neo4j or Amazon Neptune. * Experience with scraping-heavy or connector-heavy ingestion systems. * Experience with LangChain, LangGraph, Haystack, LlamaIndex, or similar orchestration frameworks. * Experience with Terraform. * Experience supporting retrieval quality, latency, and production reliability.
Nice-to-Have: * Experience with reranking, hybrid retrieval, or evaluation of retrieval quality. * Experience with AI agent workflows or tool-calling systems. * Experience with data governance, permissions, or enterprise knowledge access. * Experience in startup or product companies where engineers own end-to-end outcomes.
Client and Domain: * Client: a software company * Country: Canada * Domain: AI/Data platform
Apply for a job Write to us in email to career@insoftex.com, in telegram @insoftex_company, or via the form below.
