Senior Software Engineer, AI

Toast; Toronto; Hybrid; CAD 145,000 - 183,000; Full time

Benefits offered by this job

Competitive compensation

Extended health and dental coverage

Employee Stock Option Plan

Flexible vacation policy

Career development support

Access to high-quality equipment

Hybrid work model

Job summary

Toast is seeking a Senior Software Engineer, AI in Toronto to develop backend systems powering LLM-driven workflows. Responsibilities include designing retrieval pipelines and collaborating with various teams to ensure technical solutions meet user needs. Candidates should have 5+ years of experience in backend systems, expertise in Python, and familiarity with cloud platforms. The role offers a hybrid work model and competitive compensation between CA$145,000–CA$183,000, plus equity.

Qualifications

• 5+ years of experience building and operating backend systems in production.
• Strong experience in search and retrieval, data pipelines, distributed systems, or API-driven service architectures.
• Proficiency in Python and experience with backend frameworks, APIs, and production infrastructure.

Responsibilities

• Design, build, and maintain backend systems powering LLM-driven workflows.
• Develop retrieval pipelines and orchestration layers for scalable AI-powered searches.
• Collaborate with teams to align technical solutions with user needs and business goals.

Skills

Backend systems

Python

Distributed systems

API-driven service architectures

Search and retrieval

LLM-powered systems

Cloud platforms

Tools

FAISS

Elasticsearch

AWS

Job description

Job Description

Toast is recruiting on behalf of this company for a Senior Software Engineer, AI to join their Engineering team in Toronto. They are looking for an experienced backend engineer who is excited to build and optimize LLM-powered systems that help users uncover meaningful business insights.

Responsibilities

• Design, build, and maintain backend systems that power LLM-driven and agentic workflows
• Develop retrieval pipelines, orchestration layers, and multi‑step agent architectures that support scalable AI‑powered search experiences
• Lead the evaluation of agentic systems using automated, offline, and human‑in‑the‑loop frameworks to measure relevance, quality, latency, and task success
• Improve retrieval and ranking systems across hybrid retrieval, re‑ranking, query rewriting, and post‑retrieval synthesis
• Optimize LLM‑powered workflows for speed, accuracy, reliability, and production readiness
• Own technical projects from concept through launch, including experimentation strategy, architecture decisions, and operational excellence
• Collaborate closely with product, infrastructure, and data teams to align technical solutions with user needs and business goals
• Stay current with advances in LLMs, retrieval systems, and agentic reasoning, and apply relevant developments to product and engineering work
• Contribute to engineering best practices that support maintainability, observability, testing, and continuous delivery

Requirements

• 5+ years of experience building and operating backend systems in production
• Strong experience in at least one of the following areas: search and retrieval, data pipelines, distributed systems, or API‑driven service architectures
• 2+ years of hands‑on experience working with search, retrieval, or ranking systems
• Experience building or evaluating LLM‑powered or agentic systems, including retrieval‑augmented generation or multi‑step workflows
• Strong software engineering fundamentals with the ability to write clean, maintainable, and well‑tested code
• Proficiency in Python and experience with backend frameworks, APIs, and production infrastructure
• Familiarity with vector databases and search platforms such as FAISS, PGVector, Pinecone, Weaviate, Elasticsearch, or OpenSearch
• Experience with cloud platforms such as AWS, GCP, or Azure in environments with scale, low‑latency requirements, and high availability
• Experience using AI coding tools to improve development workflows
• A customer‑focused mindset with the ability to connect technical decisions to user outcomes
• Demonstrated ability to lead projects, make sound architectural decisions, and support the growth of others on the team

Benefits

• Competitive compensation with a salary range of CA$145,000–CA$183,000, plus equity
• Extended health and dental coverage starting from day one
• Employee Stock Option Plan for full‑time employees
• Flexible vacation policy designed to support rest and balance
• Career development support through coaching, feedback, and performance reviews
• Access to high‑quality equipment and tooling
• Hybrid work model with in‑office collaboration in Toronto on designated days
• Opportunities to work closely with leadership and contribute to meaningful technical direction
• A workplace that values belonging, authenticity, accessibility, and professional growth
• An inclusive hiring approach that considers potential, transferable experience, and equivalent backgrounds