Software Engineer

About the Role:

We’re looking for an inventive AI Research Engineer to help pioneer next-generation language model systems at the frontier of applied AI. In this role, you’ll help build foundational agent and RAG infrastructure, shape internal research initiatives, and accelerate the delivery of LLM-powered features to end users.

You’ll collaborate cross-functionally with engineering and product teams to experiment, evaluate, and deploy cutting-edge AI methods that are both scalable and production-ready.

Key Responsibilities:

• LLM System Development: Research, prototype, and build systems powered by large language models, focusing on reliability, efficiency, and relevance.
• Agent & RAG Architectures: Design and refine agentic workflows and retrieval-augmented generation pipelines that improve performance, accuracy, and cost-efficiency.
• Evaluation & Alignment: Develop metrics and tools to measure model performance, groundedness, and behaviour; explore fine-tuning and alignment techniques.
• Collaboration & Experimentation: Work closely with software engineers and product managers to test ideas and bring innovative features to life.

Requirements:

• NLP & ML Background: Strong experience in deep learning and natural language processing, with an emphasis on large language models.
• Tooling Fluency: Comfortable with libraries like Hugging Face, LangChain, or PyTorch, and evaluation frameworks.
• Production Readiness: Prior experience shipping AI models into live environments, with attention to reliability and observability.
• Research Mindset: Curious and methodical, with the ability to turn novel ideas into functional systems.
• Communication Skills: Able to clearly articulate findings, trade-offs, and next steps to both technical and non-technical stakeholders.