What you’ll bring to the table:

- 3–5 years of software engineering experience, including hands-on AI or machine learning application development.
- AWS Bedrock: Two end to end project implementation
- Hands-on experience with AI Document Intelligence
- Strong programming skills in Python and experience with another modern language such as TypeScript, JavaScript, Java, C#, or Go.
- Experience building backend applications, APIs, and cloud-native services using Microsoft Azure, AWS, or Google Cloud.
- Hands-on experience with LLM platforms such as Microsoft Foundry, AWS Bedrock, Google Vertex AI, OpenAI, Anthropic, or open-source models.
- Practical experience with RAG, embeddings, vector databases, prompt engineering, AI agents, and model evaluation.
- Solid understanding of software and AI architecture principles, including design patterns, distributed systems, vector search, MLOps/LLMOps, and emerging standards such as MCP.
- Experience with Docker, Git, automated testing, CI/CD, and contemporary software development practices.
- Demonstrated use of AI-assisted development tools such as GitHub Copilot, Cursor, or Claude Code to improve productivity, testing, code quality, and documentation.
- Strong troubleshooting, communication, and collaboration skills,



with the ability to clearly explain technical approaches and trade-offs.

What you’ll do:

- Build and maintain production-ready AI applications using LLMs, RAG, semantic search, and agentic workflows.
- Develop backend services, APIs, and integrations connecting AI solutions with enterprise systems, data sources, and cloud platforms.
- Build reusable agent components involving orchestration, tool use, memory, state management, and workflow automation.
- Implement document ingestion, chunking, embeddings, vector search, prompt workflows, and retrieval optimization.
- Develop evaluation, monitoring, and reliability processes to measure accuracy, hallucination, robustness, latency, safety, and cost.
- Contribute to CI/CD pipelines, containerized deployments, infrastructure-as-code, and MLOps/LLMOps practices.
- Apply secure and responsible AI practices, including access controls, guardrails, content filtering, prompt-injection protection, auditability, and human review.
- Collaborate with engineers, architects, data scientists, DevOps teams, and business stakeholders to deliver customer-facing AI solutions.
- Write clean, tested, maintainable code and clear technical documentation.

📌 AI Software Developer (Canada)
🏢 Nexvant Solutions
📍 Canada