Senior Data/AI Engineer
Guidepoint17 days ago
Toronto, CanadaSenior
Responsibilities
- Design, build, and operate scalable low-latency backend services and APIs for generative AI features.
- Own the full lifecycle of AI-powered applications, including design, development, deployment, monitoring, and production optimization.
- Improve retrieval-augmented generation quality through retrieval tuning, re-ranking, chunking strategies, and prompt engineering.
- Integrate LLMs with proprietary knowledge repositories, external APIs, and real-time data streams to build copilots and research assistants.
- Establish LLMOps practices including automated evaluation, observability, monitoring, and performance optimization.
- Evaluate prompt-engineering and model-interaction strategies to improve the performance and safety of proprietary and open-source LLMs.
- Provide technical leadership through code reviews, mentorship, and design discussions.
- Partner with product and business stakeholders to define technical requirements, priorities, and AI product roadmaps.
Requirements
- Bachelor’s degree in Computer Science, Engineering, or a related technical field with 6+ years of professional experience, or a master’s degree with 4+ years of professional experience in backend software engineering and generative AI.
- Proven experience designing, building, and scaling distributed, production-grade systems.
- Deep expertise in Python, a major backend framework such as FastAPI or Flask, and asynchronous programming such as asyncio.
- Experience with API design, testing, CI/CD, observability, monitoring, alerting, high uptime, and zero-downtime deployments.
- Hands-on experience deploying and managing applications on Azure, AWS, or GCP using Docker, Kubernetes, and Helm.
- At least 2 years of experience building applications that use LLMs from providers such as OpenAI, Anthropic, or Google Gemini.
- Required experience with RAG, hybrid search using vector databases such as Pinecone or Elasticsearch, multi-agent systems with tool calls, and prompt engineering.
- Experience designing evaluation frameworks for LLM systems, including rubric-based scoring, LLM Judges, or MLflow, as well as monitoring performance and drift.
- Familiarity with large-scale data processing platforms and tools such as Databricks and Apache Spark.
- Practical experience with LangChain or LlamaIndex for building LLM-powered applications.
- Demonstrated ability to lead complex technical projects and mentor other engineers.
Benefits
- Hybrid position based in Toronto.
- Paid time off.
- Comprehensive benefits plan.
- Company RRSP match.
- Development opportunities through LinkedIn Learning.
- Eligible for an annual discretionary performance bonus.
Tech Stack
Apache SparkAWSAzureDatabricksDockerElasticsearchFastAPIFlaskGoogle Cloud PlatformHelmKubernetesMLflowPython
Categories