Jr. AI Native Engineer

Overview

Valtech is hiring a Jr. AI Native Engineer to design, prototype and build intelligent digital products and experiences with multidisciplinary teams, combining software engineering fundamentals with modern AI capabilities.

What you'll do

• Design, build and ship AI-native applications and experiences for real-world use cases.
• Build applications using large language models, generative AI APIs and agentic architectures.
• Develop high-quality software using Python, TypeScript/JavaScript or comparable modern languages.
• Work with models and platforms such as Azure OpenAI, OpenAI, Anthropic Claude, Google Gemini and open-source models.
• Build RAG and knowledge-retrieval solutions using embeddings, semantic search, vector databases and enterprise data.
• Experiment with AI agents, tool/function calling, structured outputs, orchestration and multi-step workflows.
• Integrate AI solutions with APIs, databases, existing platforms and enterprise systems.
• Rapidly prototype new ideas, test assumptions and turn promising experiments into scalable solutions.
• Build approaches for evaluating and testing AI systems, considering quality, accuracy, reliability, latency and cost.
• Use AI-assisted engineering tools to explore new ways of designing, developing, testing and maintaining software.
• Apply sound engineering practices around security, privacy, responsible AI, observability and human oversight.
• Share what you're learning and contribute to the evolving AI engineering practices across Valtech.

What you'll need

• 2–4 years of professional software engineering or application development experience.
• Strong programming experience with Python, TypeScript/JavaScript or another modern programming language.
• Solid software engineering fundamentals, including application architecture, APIs, testing, debugging, version control and CI/CD.
• Hands-on experience building with generative AI, whether through client work, production applications, prototypes, internal innovation, hackathons, open-source contributions or substantial personal projects.
• Practical experience working with LLMs and model APIs, including prompting, context management, structured outputs and model selection.
• Familiarity with RAG, embeddings, semantic search or vector databases.
• Exposure to agents, function/tool calling or AI workflow orchestration.
• Experience connecting applications to APIs, data sources, databases and cloud services.
• An understanding that building a great AI demo and building a dependable AI product are two very different challenges.
• A demonstrated habit of exploring emerging technology and turning your curiosity into something tangible.

Nice to have

• Built your own AI application, agent, copilot or developer tool.
• Experimented with multiple models and learned where each performs well, and where it doesn't.
• Built RAG solutions using real-world or enterprise data.
• Explored agentic architectures, tool use or multi-agent workflows.
• Worked with frameworks such as Semantic Kernel, LangChain, LangGraph or LlamaIndex.
• Used technologies such as Azure AI Search, Elasticsearch, pgvector, Pinecone, Qdrant or Weaviate.
• Built applications on Azure, AWS or Google Cloud.
• Used tools such as GitHub Copilot, Claude Code or Cursor as part of your engineering workflow.
• Created evaluations or testing approaches for AI outputs.
• Participated in AI hackathons, internal innovation initiatives or open-source communities.

Details

• Location: Canada, remote.