高级软件开发工程师，大语言模型基础设施
Senior Software Developer, LLM Infrastructure
### **打造人们喜爱的产品**
Wealthsimple 是加拿大的领先金融创新者。公司提供一系列简单而先进的金融产品，涵盖管理投资、自助交易、加密货币、税务申报、消费和储蓄。Wealthsimple 目前为超过 400 万加拿大用户提供服务，管理的资产超过 1550 亿美元。公司由一群金融专家和技术创业者于 2014 年创立，总部位于加拿大多伦多。
我们为自己所构建的一切感到自豪——而我们才刚刚开始。阅读我们的 [文化手册](https://www.wealthsimple.com/en-ca/culture) 并了解更多 [我们的工作方式](https://www.wealthsimple.com/en-ca/careers)。
**机器学习基础设施团队**
机器学习基础设施团队构建了支撑 Wealthsimple 全面 AI 和生成式 AI（GenAI）计划的核心基础架构。随着我们 AI 的影响力不断扩大，我们的重点是构建可扩展、成本效益高的基础设施，利用开源模型和供应商解决方案实现高性能推理。我们的职责包括：
- 构建并维护在云/GPU 系统上可靠地托管和提供开源大语言模型（LLM）的基础设施。
- 实现智能模型路由框架，以优化性能、成本和延迟。
- 开发评估和基准测试工具（Evals），用于在不同使用场景中测试、验证和比较模型性能。
- 制定公司范围内运行可扩展 LLM 基础设施的技术方向。
**职位描述**
作为机器学习基础设施团队的高级软件工程师，您将设计和实现支撑我们 AI 系统的核心后端和基础设施。您将与数据科学家、平台工程师和工程领导紧密合作，高效且安全地扩展我们的生成式 AI 覆盖范围。
在此职位中，您将有机会：
- 构建模型路由架构（例如集成 LiteLLM），动态地将请求分配到内部和外部模型。
- 配置和管理高性能 GPU 基础设施，用于提供开源大语言模型。
- 构建评估框架（Evals），使工程师和数据科学家能够根据生产需求对模型质量进行基准测试。
- 推动关键的成本优化和基础设施效率项目，同时不牺牲系统的准确性或可靠性。
**我们寻找具备以下条件的人：**
- 6 年以上软件工程经验，构建生产级分布式系统
查看英文原文
### **Build something people love**
Wealthsimple is Canada’s leading financial innovator. The company offers a full suite of simple, sophisticated financial products across managed investing, do-it-yourself trading, cryptocurrency, tax filing, spending and saving. Wealthsimple currently serves more than 4 million Canadians and holds over $155 billion in assets under administration. The company was founded in 2014 by a team of financial experts and technology entrepreneurs, and is headquartered in Toronto, Canada.
We're proud of what we've built — and we're just getting started. Read our [Culture Manual](https://www.wealthsimple.com/en-ca/culture) and learn more about [how we work](https://www.wealthsimple.com/en-ca/careers).
**Machine Learning Infrastructure Team**
The Machine Learning Infrastructure team builds the core foundation powering AI and GenAI initiatives across Wealthsimple. As our AI footprint expands, our priority is building scalable, cost-effective infrastructure that enables high-performance inference using open-source models alongside vendor solutions. Our responsibilities are to:
- Build and maintain infrastructure to host and serve open-source LLMs reliably on cloud/GPU systems.
- Implement intelligent model-routing frameworks to optimize performance, cost, and latency.
- Develop evaluation and benchmarking tooling (Evals) to test, validate, and compare model performance across use cases.
- Set the technical direction for operating scalable LLM infrastructure company-wide.
**The Role**
As a Senior Software Engineer on the ML Infrastructure team, you will design and implement the core backend and infrastructure powering our AI systems. You will work closely with data scientists, platform engineers, and engineering leaders to scale our GenAI footprint efficiently and securely.
In this role, you will have the opportunity to:
- Build model-routing architecture (e.g., LiteLLM integration) to dynamically direct requests across internal and external models.
- Provision and manage high-performance GPU infrastructure for serving open-source LLMs.
- Build evaluation frameworks (Evals) that enable engineers and data scientists to benchmark model quality against production requirements.
- Drive key cost-optimization and infrastructure efficiency initiatives without sacrificing system accuracy or reliability.
**We are looking for people who have:**
- 6+ years of software engineering experience building production-ready distributed systems or data platform infrastructure.
- Strong proficiency in **Python** and infrastructure tooling like **Kubernetes** and **Terraform**.
- Proven experience designing and operating highly performant, observable backend systems.
- Practical experience or deep familiarity with the modern AI ecosystem (e.g., serving open-source models, vLLM, Ray, model routing, or evaluation frameworks).
- Track record of owning technical projects end-to-end with high autonomy.
**Our stack includes:**
- **Container & Infra:** Kubernetes, Terraform, AWS GPU infrastructure
- **Languages & APIs:** Python, FastAPI
- **LLM Tooling & Serving:** LiteLLM, vLLM, Ray, Bedrock
- **Data & Streaming:** Kafka, Postgres, Redshift, Snowflake
### **Why Wealthsimple?**
🌸 Top-tier health benefits and life insurance
📈 Long-term group savings with employer match, through Wealthsimple for Business
🌴 20 vacation days, 4 wellness days, and unlimited sick and mental health days per year
✈️ 90 days away: work outside Canada for up to 90 days per year
👥 Employee resource groups, including Rainbow (2SLGBTQ), Women of WS, and Black at WS
🌎 We are a hybrid team with over 1,500 employees across North America. The people are one of the best parts of working here: you'll collaborate with incredibly talented, curious, and driven teammates who are deeply committed to doing great work.
### **ICYMI**
**Technology & Innovation at Wealthsimple:** We move quickly and build thoughtfully. That means we're always looking for better ways to work — whether that's new tools, AI, or rethinking how we approach a problem. We don't expect you to have all the answers, but we do expect curiosity and a willingness to evolve alongside the products we're building.
**Inclusion Statement:** We're building products for a diverse world, and we need a diverse team to do it well. We strongly encourage applications from everyone, regardless of race, religion, colour, national origin, gender, sexual orientation, age, marital status, or disability status.
**Accessibility Statement:** We're committed to an accessible hiring experience. If you need any accommodations throughout the interview process, please let us know — we'll work with you to make sure you have what you need. We also welcome any feedback on how we can better accommodate candidates with accessibility needs.
**AI in Hiring:** We may use artificial intelligence (AI) tools to support parts of our hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our team but don't replace human judgment – all final hiring decisions are made by people. If you have questions about how your data is used, reach out to us.