Senior AI-Powered Retrieval & Agent Engineer

GuruLink; Toronto; Hybrid; CAD 110,000 - 170,000; Full time

Job summary

GuruLink is helping a Toronto-based, fast-growing B2B SaaS company hire a Senior Software Engineer to build state-of-the-art, LLM-powered agent systems that reason, plan, and automate workflows. You’ll own architecture through production, integrating retrieval-augmented generation and dense retrieval for fast, trusted search at scale.

You’ll design and optimize the retrieval and ranking pipelines, collaborate with product, infra and data teams, and relentlessly improve latency and quality for

Qualifications

• Production experience with backend systems — search/retrieval, data pipelines, distributed systems, or API-heavy services.
• Hands-on experience building or improving retrieval, search, or ranking pipelines.
• Experience building and/or evaluating agentic or LLM-powered systems (RAG, multi-step agents).
• Strong Python and software engineering fundamentals (testing, CI/CD, observability).
• Experience with vector databases (FAISS, PGVector, Pinecone, Weaviate, Elasticsearch, or OpenSearch).
• Experience with cloud infrastructure at scale (AWS, GCP, or Azure).
• Regular use of AI coding tools (Copilot, Cursor, Claude Code, or similar).
• Track record of shipping features tied to real user/business outcomes.
• Ability to own a project end-to-end and provide technical direction.

Responsibilities

• Build and ship backend systems powering agentic workflows — retrieval pipelines, orchestration layers, and multi-step agent architectures that turn millions of data points into actionable intelligence.
• Own evaluation of agentic systems at scale — build and operate evaluation frameworks (automated, offline, human-in-the-loop) measuring relevance, quality, latency, and end-to-end task success.
• Design and optimize retrieval and ranking systems — hybrid retrieval, re-ranking, query rewriting, and post-retrieval synthesis, with a clear grasp of the tradeoffs between BM25, dense retrieval, and hybrid approaches.
• Improve LLM-powered workflows end to end — prompt design, retrieval strategy, caching, and latency optimization.
• Ship with the customer in mind — connect technical decisions to customer outcomes and business impact, iterate quickly, and course-correct based on measured results.
• Collaborate across product, infrastructure, and data teams, and help establish patterns/best practices for production-grade agentic systems.
• Stay current on advances in LLMs, retrieval architectures, and agentic reasoning.

Skills

Backend systems

Retrieval pipelines

Agentic/LLM systems

Python

Vector databases

Cloud infrastructure

AI coding tools

Project ownership

Tools

FAISS

Pinecone

Elasticsearch/OpenSearch

Weaviate

Job description

GuruLink is helping a Toronto-based, fast-growing B2B SaaS company hire a Senior Software Engineer to build state-of-the-art, LLM-powered agent systems that reason, plan, and automate workflows. You’ll own architecture through production, integrating retrieval-augmented generation and dense retrieval for fast, trusted search at scale.

You’ll design and optimize the retrieval and ranking pipelines, collaborate with product, infra and data teams, and relentlessly improve latency and quality for