Yolando Logo

Yolando

Senior Software Engineer

Reposted 4 Days Ago
Be an Early Applicant
Hybrid
Toronto, ON, CAN
Senior level
Hybrid
Toronto, ON, CAN
Senior level
Lead design and implementation of production AI/LLM systems and scalable FastAPI backends, implement embedding-based semantic search with PostgreSQL/pgvector, build WebSocket real-time collaboration, own GCP/Kubernetes infrastructure (KEDA, Terraform), and mentor engineers while driving architectural decisions and feature rollouts.
The summary above was generated by AI
About Us

The search bar is becoming a conversation. Brands need to know how to get found by AI, and that's what we do. Yolando is the platform that helps marketers understand and improve how AI models discover, cite, and recommend their brand.

We've raised $8.5M from Drive Capital and MaRS Discovery District. We're 15 people building the standard for Generative Engine Optimization.

Role Overview

We are looking for a Senior Software Engineer to drive the technical direction of Yolando, our flagship AI Search Optimization platform. You will own AI/LLM systems end-to-end, designing production agents using Pydantic AI for content generation and competitive intelligence. As a technical leader, you will architect scalable backend services using FastAPI and PostgreSQL, build real-time collaborative systems with WebSockets, and mentor engineers to establish patterns that scale.

Key Responsibilities
  • Own AI/LLM Systems End-to-End: Design and build production AI agents using Pydantic AI for content generation, brand analysis, and competitive intelligence. Implement tool-based architectures that enable agents to explore signals and generate recommendations at scale.

  • Architect Scalable Backend Services: Build and evolve FastAPI microservices that power real-time content workflows, handling complex state machines for onboarding, content generation, and recommendation pipelines. Optimize PostgreSQL with pgvector for embedding-based semantic search and deduplication.

  • Build Real-Time Collaborative Systems: Implement WebSocket-based real-time collaboration features, including document synchronization, streaming AI responses, and live status updates using technologies like Yjs CRDTs.

  • Drive Infrastructure Excellence: Own service deployment on GCP/Kubernetes with KEDA event-driven autoscaling. Design ScaledJobs for background processing, implement zero-downtime migrations, and establish observability patterns with Logfire.

  • Lead Technical Direction: Mentor engineers, drive architectural decisions, and establish patterns that scale. Own complex features from design through production rollout, coordinating across frontend and data engineering teams.

What We're Looking For
  • 5+ years backend engineering with Python and production experience with FastAPI or similar async frameworks.

  • Proven track record building AI/LLM-powered applications in production (prompt engineering, agent architectures, tool use patterns).

  • Deep experience with PostgreSQL, including query optimization, indexing strategies, and migrations at scale.

  • Strong understanding of distributed systems: event-driven architectures, background job processing, caching patterns.

  • Experience with GCP, Kubernetes, and Terraform for production infrastructure.

  • Track record of technical leadership: mentoring, architectural decision-making, cross-team coordination.

  • Ownership mindset: you drive features end-to-end, from design through production support.

Bonus if you have:
  • Experience with vector databases (pgvector, Pinecone) and embedding-based search/RAG systems.

  • Background in real-time systems: WebSockets, CRDTs, collaborative editing.

  • Familiarity with Pydantic AI or similar structured LLM frameworks.

  • Experience with KEDA or other event-driven autoscaling patterns.

  • Background in SEO, content marketing, or marketing technology.

Our Stack
  • Backend: Python 3.11, FastAPI, SQLModel, PostgreSQL/pgvector, Pydantic AI, Redis

  • Frontend: Next.js 14+ (App Router), React 19, TypeScript, Plate.js, Radix UI

  • Infrastructure: GCP (Cloud Run, Pub/Sub, AlloyDB), Kubernetes, KEDA, Terraform, GitHub Actions

  • Observability: Logfire, PostHog

  • Data: Databricks, Protocol Buffers, Alembic migrations

Why Join Us?
  • Join an innovative, fast-growing startup building cutting-edge AI marketing solutions.

  • Make a meaningful impact by shaping the platform's user experience, design identity, and overall success.

  • Dynamic environment with opportunities for real ownership, learning, and growth.

  • Competitive salary and support for professional development.

How to Apply
  • Please send your resume and a brief note about why you're interested in joining us.

  • We'd love to see your work and hear your story!

  • This is a hybrid role, with 4 days per week in our downtown Toronto office.

Similar Jobs

Yesterday
Easy Apply
Hybrid
Toronto, ON, CAN
Easy Apply
Senior level
Senior level
HR Tech • Payments • Professional Services • Software
Build and own core components of an LLM-powered agent platform: orchestration, tool integrations, APIs, knowledge/memory infrastructure, trust & safety, and evaluation tooling. Partner with Operations to translate workflows into agent capabilities, mentor teammates, and ship production-ready, scalable AI-native systems.
Top Skills: AWSC#CircleCIDatadogDockerElasticsearchGitGoJavaJavaScriptKafkaKubernetesLlmsMemcacheMySQLPythonRagRedisRuby On RailsTerraformVuejs
5 Days Ago
Easy Apply
Remote or Hybrid
Canada
Easy Apply
Senior level
Senior level
Artificial Intelligence • Cloud • Computer Vision • Hardware • Internet of Things • Software
Lead backend engineering for AI-powered, real-time in-vehicle experiences. Define architecture and APIs for edge-constrained clients, build orchestration for concurrent agent/voice interactions, ensure reliability, observability, and safety of AI systems, mentor firmware engineers, and ship zero-to-one products.
Top Skills: Agent Orchestration FrameworksAi Agent PlatformsClaude CodeCodexCursorEdge ComputingEmbedded SystemsGoLlmsPython
6 Days Ago
In-Office or Remote
CA
Senior level
Senior level
Blockchain • eCommerce • Fintech • Payments • Software • Financial Services • Cryptocurrency
Lead design and operation of Block's real-time, event-driven data systems. Build and run high-throughput streaming pipelines, turn Kafka event streams into low-latency data products, improve reliability and observability, mentor engineers, and define platform architecture and standards for projections, third-party data proxy, and graph data capabilities.
Top Skills: AWSBlock-ForgeCloudeventsDatabricksDatahubDbtFlinkIcebergKafkaKotlinPrefectSnowflakeSparkSpark Structured Streaming

What you need to know about the Toronto Tech Scene

Although home to some of the biggest names in tech, including Google, Microsoft and Amazon, Toronto has established itself as one of the largest startup ecosystems in the world. And with over 2,000 startups — more than 30 percent of the country's total startups — Toronto continues to attract new businesses. Be it helping entrepreneurs manage their finances, simplifying business operations by automating payroll or assisting pharmaceutical companies in launching new drugs, the city's tech scene is just getting started.

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account