About Us

Railtown AI is a mid-size startup at the forefront of AI development based in the heart of downtown Vancouver. We foster an exciting, creative environment where your ideas can thrive. Our flagship product, Conductr, integrates with codebases, ticketing systems, and error-tracking tools to boost developer productivity. As our suite of AI offerings expands rapidly, we're looking to strengthen our team with a senior ML engineer who can help bring our next generation of products to life.

Role Overview

We're seeking a seasoned engineer to tackle complex software-design challenges around LLM integration and to evolve our core framework. You will:

• Develop & Refine: Architect and enhance a Python framework that interfaces with large language models alongside our existing AI team.
• Drive Product Development: Apply your expertise to additional AI tools across our product line.
• Leverage Transformer Knowledge: Use your deep understanding of transformer-based architectures and the ML lifecycle to guide design decisions.
• Lead & Communicate: Own technical decisions, collaborate closely with colleagues, and clearly articulate trade-offs and progress to stakeholders.

Key Responsibilities

• Improve Architecture: Design a flexible, efficient, and scalable Python framework for multi-agent orchestration of LLMs.
• Optimize Performance: Employ concurrency and multithreading to boost throughput and reliability; diagnose and resolve integration bottlenecks.
• Stay Current: Monitor Python ecosystem trends and LLM advancements; propose and prototype new tools, libraries, or patterns.
• Provide Leadership: Make informed decisions, guide engineering peers, and champion best practices in code quality and documentation.
• Solve Complex Problems: Apply creative, thoughtful design to overcome challenges and outpace larger competitors.

Key Qualifications

• BS or MS in Computer Science, Engineering, Statistics, Applied Mathematics, or a related quantitative discipline.
• 5+ years of professional Python development, with strong object-oriented design and software-engineering principles.
• Proven experience building concurrent or multithreaded Python systems.
• Hands-on experience with LLM frameworks (e.g., HuggingFace, LiteLLM, LangChain, LlamaIndex).
• Familiarity with agile methodologies (version control, Kanban processes, cloud deployment).
• Experience with deep-learning frameworks (PyTorch and/or TensorFlow) is a plus.
• Contributions to or management of open-source projects are a plus.
• Prior experience leading an engineering team is preferred.

What We Offer

• Stock options and a competitive salary
• A transit-accessible office location
• 2 days in office/3 days at home
• Flexible hours

How to Apply

Send your resume highlighting your Python-framework work and LLM projects to [email protected] or apply via this posting.