AI Engineer Generative AI & Agentic Systems

Summary

Do you want to build AI that actually ships Were looking for an engineer who thinks in systems writes productiongrade code and gets excited about transforming cuttingedge LLMs into reliable scalable solutions.

As an AI Engineer at Bell youll design and build the next generation of AIpowered applications. This includes architecting agentic pipelines wrapping models in robust APIs and embedding Generative AI directly into products that support millions of customers and internal teams. Youll collaborate closely with senior engineers and product partners to move quickly iterate thoughtfully and deliver solutions that perform in the real world.

Were seeking someone who genuinely enjoys the craft someone who tackles complex problems handson enjoys exploring new tools and techniques and finds satisfaction in solving challenges that dont always come with obvious answers. The AI landscape is evolving rapidly and we value engineers who are curious adaptable and eager to grow alongside youve been building with LLMs from prompt engineering and RAG pipelines to toolcalling agents and multistep orchestration and you have the backend expertise to bring these solutions into production this role offers the opportunity to make a real impact.

Key Responsibilities

• Design and implement multi-step AI agents using orchestration frameworks (e.g. LangChain LlamaIndex CrewAI or custom builds) systems that reason use tools retrieve context and take action.
• Write clean production-ready Python to build APIs microservices and backend logic that powers AI features end-to-end from prompt to response.
• Build and maintain RESTful (and event-driven where appropriate) APIs that serve AI capabilities reliably across teams and applications.
• Rapidly prototype interactive demos using Streamlit or lightweight front-end tooling then follow through to scalable maintainable implementations.
• Integrate state-of-the-art models for text image and video (e.g. Gemini Nano Banana Veo) into internal tools and customer-facing products.
• Participate in system design discussions and contribute an engineering perspective on how to build things that scale.
• Partner with end users data engineers and product owners to deeply understand user needs and the full user journey then translate those insights into technical solutions that actually solve the right problem.

Critical Qualifications

• Bachelors degree in Computer Science Software Engineering or a related technical field or equivalent professional experience
• 3 years of professional software or AI engineering experience. You write production-grade code not just research scripts.
• Strong Python skills including experience building APIs with FastAPI or Flask. SQL proficiency is expected.
• Hands-on LLM experience: Youve worked directly with LLM APIs (OpenAI Gemini Anthropic etc.) and understand the practical realities prompt design context management latency cost and failure modes.
• Agentic or RAG systems experience: Youve built at least one system involving tool use retrieval-augmented generation multi-step reasoning or autonomous agents not just single-shot completions.
• Cloud platform experience: GCP preferred; AWS or Azure acceptable.
• Engineering mindset: You approach problems with rigor break them down systematically and know how to balance speed with quality.
  
  

Preferred Qualifications

• Experience with AI orchestration frameworks such as Google ADK (Agent Development Kit) LangChain LlamaIndex LangGraph CrewAI or similar.
• Familiarity with vector databases (e.g. Pinecone Weaviate pgvector) for semantic search and retrieval.
• Understanding of CI/CD pipelines Git-based workflows containerization (Docker) and model deployment practices.
• Exposure to event-driven architectures async processing or streaming responses (e.g. SSE WebSockets).
• Experience building Generative AI applications involving media image or video generation.
• Bilingual in French and English (an asset).