Staff Software Engineer

This is a hands-on technical leadership role: you’ll ship across the stack, raise the bar for how we build, and work closely with product, design, AI, and customers to deliver dependable outcomes in demanding enterprise environments., LLM Systems & Agents

• Architect and build production LLM pipelines and multi-step agents, including tool use, retrieval, orchestration, and memory.
• Treat reliability as a first-class concern: design for graceful degradation, retries, fallbacks, guardrails, and bounded failure modes.
• Reduce hallucinations and unpredictable behavior through improved prompting strategies, structured outputs, validation, and grounding.
• Optimize cost and latency across models, context strategies, caching, and routing.

Evaluation & Observability

• Develop the evaluation and observability layer: offline evals, regression suites, tracing, and live monitoring of quality, cost, and latency.
• Monitor system performance and proactively resolve complex production issues.

Platform & Application Development

• Design and operate the scalable backend systems and data pipelines that support the LLM layer.
• Ship production-ready features across front-end and back-end systems with strong attention to detail.
• Work with cloud-based infrastructure and CI/CD pipelines to ensure smooth, safe, and frequent releases.

Technical Leadership & Collaboration

• Establish engineering standards and patterns for LLM development across the broader team.
• Maintain high standards for code quality through rigorous reviews, testing, and documentation; mentor junior and intermediate engineers.
• Partner with product and engineering peers to assess feasibility and prototype rapidly.
• Work directly with customers when necessary to help optimize complex enterprise workflows in our application.

• Bachelor’s degree in Computer Science, a similar technical field, or equivalent practical experience.
• 7+ years of professional software development experience, with a proven track record of building and maintaining complex, full-stack applications.
• Hands-on experience building, benchmarking, and operating LLM-powered systems in production (pipelines, multi-step agents, advanced RAG, or similar).
• Demonstrated experience owning architecture for distributed systems and raising engineering standards across a team.

Ranger AI Tech Stack

• App: NextJS, NestJS, Python
• Data: PostgreSQL, Vector Databases / Hybrid Search
• Infrastructure: AWS (ECS, S3, RDS), Docker, CI/CD
• AI: LLM APIs, embedding pipelines, agent orchestration, evaluation tooling

• Compensation: Base salary of CAD 175,000 plus competitive equity considerations (post-90 days), depending on experience and impact.
• Benefits: Extended health benefits package + PTO
• The opportunity to shape the technical foundation of a fast-growing AI startup transforming a massive global industry.

Ranger AI is a venture-backed intelligence platform helping the world reindustrialize through digital and AI transformation. Backed by top-tier investors including Bonfire, Inovia, 25Madison and Panache Ventures, our core focus revolves around revolutionizing the tendering and RFP process for industrial manufacturing companies through the power of AI agents. Our platform drastically improves how enterprise companies manage Proposal/Quotation workflows through superior data quality, faster response times, and a highly consistent customer experience.