Vosyn Applied AI Engineer (Agentic Workflows & RAG) - Masters-Level Internship Department: Software Development

Vosyn; Toronto; Hybrid; CAD 37,000 - 51,000; Part time

Job summary

Vosyn invites a Masters-level intern to shape the intelligence layer of agentic workflows, LLM grounding, and RAG integrations. You will select models, craft prompts, and evaluate non-deterministic AI features while collaborating across teams to deliver production-ready components.

The role offers remote work with hybrid options in Toronto, compensation at CAD 32 per hour, and a path toward future opportunities as Vosyn scales for IPO readiness.

Qualifications

• Master’s program enrollment or completion is mandatory.
• Hands-on experience with AI coding assistants and the Claude API or comparable model APIs preferred.
• Strong understanding of LLM behavior: context windows, reasoning vs instruction models.

Responsibilities

• Design and harden agentic workflows that plan and act reliably.
• Build retrieval (RAG) pipelines grounded in client data.
• Choose models for tasks and justify latency/cost/quality trade-offs.
• Engineer prompts and context structures for model classes.
• Write evaluations to prove system correctness rather than plausibility.
• Integrate AI tools with internal systems via APIs or MCP.
• Review AI-generated code and workflows for security and safety.
• Document workflows, prompts, and integrations in Notion.

Skills

Agentic workflows

RAG pipelines

Prompt engineering

Evaluation mindset

API integration

Cross-functional collaboration

Model selection

Documentation

Education

Master’s degree in CS/SE/AI

Tools

Claude API

MCP (Model Context Protocol)

GitHub

Notion

Job description

Job Openings › Applied AI Engineer (Agentic Workflows & RAG) - Masters-Level Internship

Applied AI Engineer (Agentic Workflows & RAG) - Masters-Level Internship

Work location: Remote (with hybrid options in Toronto)

Compensation: Hourly ($32 CAD)

About Us

Vosyn is a Language Synthesis AI company based in Toronto. We build technology that removes language barriers, so people can access and understand information in any language. We are preparing for an IPO, and the people who join us now help shape both the product and the company itself. Good ideas get heard here, whoever they come from.

About the Role

We are seeking a sharp, technically deep Applied AI Engineer Intern to own the intelligence layer of what we build. This role is ideal for a Master’s level student who does more than use AI coding tools - you understand how modern language and reasoning models actually behave, and you build with them as components. You will design and ship agentic workflows (systems where a model plans, acts, and re-plans in a loop), build retrieval-augmented generation (RAG) and search integrations that ground AI in real, current data, choose the right model for each job, and write the evaluations that prove the system works rather than just appears to. This is the role that delivers the “AI” in AI consulting: when a client has a scoped roadmap, you are the person who stands the tool up.

Key Responsibilities

• Design, build, and harden agentic workflows that plan and take actions reliably - and understand why agents fail (context loss, compounding errors, no feedback signal) and how to structure tasks so they succeed.
• Build retrieval (RAG/search) pipelines that fetch the right client data and ground model outputs in it, integrated into core applications rather than demos.
• Select the right model for each task - reasoning model vs. fast instruction model - and be able to justify the trade-off in latency, cost, and quality.
• Engineer prompts and context structures appropriate to the model class, including knowing when reasoning models need framing rather than step-by-step hand-holding.
• Write evaluations for AI features, because with non-deterministic models “it worked once” is not evidence that it works.
• Connect AI tools to internal systems and data sources via APIs or MCP to power real client use cases.
• Review and validate AI-generated code and automated workflows critically for correctness, security, and safety.
• Collaborate with the Builder and the Integration & Data Engineer to deliver complete, working solutions, and document workflows, prompts, and integrations in Notion.

About You

• Currently enrolled or recently graduated from a Master’s program in Computer Science, Software Engineering, AI/ML, Information Systems, or a related field. Master’s program enrollment or completion is mandatory.
• Strong, demonstrable hands‑on experience with AI coding assistants and the Claude API or comparable model APIs - portfolio, GitHub, or live examples strongly preferred.
• A working understanding of how modern LLMs and reasoning models behave: context windows, the difference between reasoning and instruction models, and when to reach for each.
• Practical experience with at least one of: building an agentic workflow, building a RAG/retrieval pipeline, or integrating models via tool calling or MCP.
• Excellent prompt‑engineering and context‑management skills.
• An instinct for evaluation: you want to measure whether the AI is actually correct, not just plausible.
• Excellent verbal and written communication skills within a cross‑functional team environment.
• We believe exceptional talent often emerges from diverse paths. If you possess a profound curiosity, a genuine passion for continuous personal and professional growth, and a strong desire to apply your unique abilities to create significant impact within our team, we strongly encourage you to apply even if your background doesn’t align perfectly with every single qualification.

Why Join Us

• Work inside a start‑up as it prepares for an IPO, and see how that actually gets done.
• Work directly with senior management and members of the advisory board.
• Build experience you can point to: real projects with real outcomes.
• Take ownership of work that matters to the company, with the pace and responsibility of a start‑up.

Vosyn is an equal-opportunity employer. We hire people from different backgrounds, disciplines, and countries because the work is better for it, and we want every member of the team to feel respected and supported. We take workplace safety seriously, follow the regulations that apply to us, and expect everyone here to look out for one another. If that sounds like a place you would want to work, we encourage you to apply.

• Agentic coding: Claude Code (primary), plus Cursor or Windsurf
• AI APIs & SDKs: Anthropic Claude API and comparable model APIs; reasoning and instruction-tuned models
• Retrieval & RAG: vector databases (e.g., pgvector, Pinecone, Weaviate), embeddings, semantic and hybrid search
• Orchestration & integration: MCP (Model Context Protocol), function/tool calling, agent frameworks
• App & data layers: React.js / Next.js, Node.js / Python, Supabase or Firebase,PostgreSQL
• Evaluation: prompt and output evaluation harnesses, test sets, regression checks for non-deterministic systems
• Version control & documentation: Git / GitHub, Notion

Recruitment Process

• 1 Apply
• 2 1st Interview
• 3 2nd Interview
• 4 3rd Interview
• 5 Group Discovery Session
• 6 Next Step Form
• 7 Contract
• 8 Onboarding

Your placement is an opportunity to contribute at a richly rewarding stage of growth, working directly with senior management and members of the advisory board while gaining an inside view of how a company develops. You will take ownership of work on the company's critical path, building experience you can carry into your next chapter, with priority consideration for full-time opportunities after your internship. If academic commitments affect your availability, share them with us so we can explore what is possible within your program's placement requirements. Thank you for considering a journey with us. We look forward to learning what you could contribute and what you hope to discover.