About the role

  • AI Engineer developing secure, enterprise-grade AI systems for Valsoft's Edelweiss Software Group portfolio. Collaborating with operators and product teams to drive rapid product innovation.

Responsibilities

  • Design, develop, and deploy production-grade, secure AI systems utilizing scalable polyglot microservices.
  • Integrate state-of-the-art enterprise LLMs (Anthropic Claude Opus 4.6, OpenAI GPT-5.2, Google Gemini 3) into SaaS platforms via dynamic, fault-tolerant API routing gateways.
  • Modernize extensive codebases using agentic swarm coding, automated refactoring tools, and cross-language translation.
  • Develop autonomous multi-agent workflows utilizing parallel orchestration tools like the OpenAI Codex and Claude Code CLI.
  • Automate comprehensive technical documentation for legacy and newly generated codebases using AI orchestration.
  • Rapidly prototype → validate via adversarial testing → deploy → iterate.
  • Apply good knowledge of software engineering design patterns and architecture to ensure the scalability and maintainability of AI-generated systems.
  • Implement complex RAG systems and continually optimize trade-offs between massive-context hydration (up to 1-million tokens) and multi-stage semantic retrieval.
  • Work extensively with vector databases (Pinecone, Weaviate, FAISS) and manage persistent document embedding queues.
  • Build polyglot microservices specifically capable of handling massive, long-running operational tasks and streaming continuous token generation via persistent connection protocols (WebSockets and Server-Sent Events).
  • Ensure SOC2 compliance, data residency (via inference_geo parameters), and deterministic execution through policy-as-code agentic governance.
  • Deploy and scale models strictly within secure managed cloud boundaries (Azure AI, AWS Bedrock, GCP Vertex) leveraging Docker and Kubernetes orchestration.
  • Architect "zero-touch deployment" CI/CD pipelines fortified with adversarial gating.
  • Design and implement unit test and benchmark automation workflows, utilizing AI agentic coding to rigorously validate and test produced code.
  • Natively integrate synthetic red teaming into CI/CD to actively prevent prompt drift, reward hacking, and logic degradation.
  • Work directly with non-technical stakeholders to translate ambiguous business problems into secure, scalable AI solutions.
  • Optimize Atlassian workflows (Jira) to automate the translation of unstructured product requirements into structured prompt contexts for AI agents.

Requirements

  • 3-5+ years of demonstrable enterprise software development experience.
  • Good knowledge of software engineering design patterns and architecture.
  • Flexible in most popular programming languages (Python, Javascript, Typescript, .Net, C#) and web frameworks (NextJS, etc.).
  • Ability to switch environments and programming using agentic programming tools to validate and test your produced code.
  • Backend development experience designing polyglot APIs, decoupled asynchronous microservices, and utilizing persistent connection protocols (WebSockets/SSE).
  • Familiarity with containerization (Docker, Kubernetes) and architecting multi-region, fault-tolerant cloud infrastructure (AWS, Azure, or GCP).
  • Enterprise LLM integration and dynamic API routing (OpenAI, Anthropic, Gemini, DeepSeek).
  • Multi-agent orchestration and advanced CLI tooling (Claude Code with Auto Hot-Reload and Forking Context, OpenAI Codex).
  • Mastery of localized AI IDE layers (Cursor for repository-wide reasoning, GitHub Copilot).
  • Massive-context RAG pipelines, dynamic chunking strategies, and vector databases (Pinecone, Weaviate, FAISS).
  • Custom evaluations (LangSmith), structured outputs, and managed fine-tuning in secure cloud boundaries.
  • Zero-touch CI/CD pipelines and advanced Git workflows (including Git worktree isolation for autonomous sub-agents).
  • Unit test and benchmark automation frameworks fully integrated with AI-driven testing.
  • Adversarial LLM testing and automated synthetic red-teaming integration.
  • Monitoring dynamic access limits and real-time atomic token/credit consumption tracking.
  • Strict hallucination mitigation, enterprise guardrails, and deterministic policy-as-code execution.

Job title

Job type

Full Time

Experience level

Mid levelSenior

Salary

Not specified

Degree requirement

No Education Requirement

Tech skills

AWSAzureCloudDockerGoogle Cloud PlatformJavaScriptKubernetesMicroservicesNext.jsPythonTypeScript

Location requirements

RemoteCanada

Report this job

Found something wrong with the page? Please let us know by submitting a report below.