GenAI Search Engineer (PL5667)

Employment Duration: 9 months

Location: Toronto, hybrid

Employment Type: Full-time

About Paralucent

Paralucent brings clarity to complex work, helping organizations move beyond complexity toward clarity through practical, thoughtful technology solutions.

Paralucent Core Values

We’re Driven to deliver real outcomes, and we Take Ownership from first question to final result. We’re Creative Problem Solvers who cut through complexity to bring clarity, and we’re Humbly Confident (high standards, low ego, always learning). Above all, we’re Customer Centric: we build with empathy, partner closely, and measure success by the impact we create for the people who rely on what we deliver.

Why This Role Matters

You will design and deliver secure, scalable enterprise search and knowledge-retrieval experiences powered by Generative AI. Working closely with product, data, architecture, security and business stakeholders, you will turn complex enterprise information into relevant, grounded, traceable and useful answers.

Key Responsibilities

• Build production-grade RAG solutions: Design and implement Retrieval-Augmented Generation pipelines for enterprise GenAI applications.

• Develop retrieval pipelines: Create document ingestion, parsing, chunking, metadata enrichment, embedding, retrieval, reranking and response-generation workflows.

• Optimise enterprise search: Implement hybrid keyword, semantic and vector search using Azure AI Search, Elasticsearch, OpenSearch or comparable platforms.

• Improve relevance and answer quality: Develop query rewriting, decomposition, contextual retrieval, grounding, citation and multi-step search capabilities.

• Integrate LLM applications: Connect commercial and open-source LLMs with structured and unstructured enterprise data sources.

• Build scalable services: Develop Python-based APIs and integrations with document repositories, databases, APIs and enterprise systems.

• Evaluate and tune solutions: Establish evaluation frameworks, monitor retrieval quality and conduct experiments across embeddings, chunking strategies, rerankers and prompts.

• Embed security by design: Ensure document-level access controls, authorisation-aware retrieval, privacy, auditability and responsible AI safeguards.

• Support production delivery: Contribute to architecture reviews, code reviews, automated testing, CI/CD, observability and production support.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Data Science, Artificial Intelligence or a related discipline, or equivalent practical experience.

• Four or more years of experience in software engineering, search engineering, data engineering, machine learning engineering or related roles.

• Strong Python programming experience, including building scalable APIs and services.

• Hands-on experience delivering LLM or Generative AI solutions.

• Practical experience designing and building RAG architectures.

• Experience with embeddings, semantic search, vector databases or vector indexes, and similarity search.

• Experience with Azure AI Search, Elasticsearch, OpenSearch or an equivalent search platform.

• Understanding of APIs, REST services, JSON, authentication and distributed application architectures.

• Experience working with structured and unstructured data, including PDF, Word, HTML and text-based content.

• Strong software engineering practices, including Git, automated testing, CI/CD and production troubleshooting.

• Ability to diagnose retrieval failures, hallucinations, poor ranking, missing context and irrelevant responses.

• Strong communication skills and the ability to translate business needs into scalable technical solutions.

Nice to Have

• Experience with Azure OpenAI, Azure AI services or comparable cloud AI platforms.

• Experience integrating with Microsoft Copilot, Microsoft Graph, SharePoint, Teams or Microsoft 365 content.

• Experience with Pinecone, Weaviate, Milvus, pgvector, FAISS or comparable vector technologies.

• Experience with Semantic Kernel, LangChain, LlamaIndex or similar orchestration frameworks.

• Experience with transformer models, embedding models and reranking models.

• Experience building agentic AI or multi-agent workflows.

• Knowledge of knowledge graphs, entity extraction, taxonomy or metadata enrichment.

• Familiarity with ML or LLM observability and evaluation tools.

• Experience deploying AI workloads using Azure, Kubernetes, Docker or container-based platforms.

If you want to do work you’re proud of, with people who own the outcome, this is your place.