Software Engineer
Rocscience
About the role
Rocscience is a global leader in geotechnical and geoenvironmental engineering software solutions. With over 30 years of expertise, we develop innovative, user-friendly tools that enable engineers and researchers to analyze and design safe, efficient, and sustainable structures. Our cutting-edge software suite supports professionals working in rock, soil, and ground engineering worldwide. At Rocscience, we foster a collaborative and forward-thinking environment where cutting‑edge technology meets practical engineering challenges, and we are committed to continuous innovation and customer success.
Role Description
Rocscience is hiring a Software Engineer to join the RSInsight AI team, the team responsible for building and scaling RSInsight, an AI‑powered platform used by thousands of engineers worldwide.
RSInsight combines modern cloud infrastructure, large language models, retrieval systems, and a desktop integration layer to enable AI‑driven workflows inside geotechnical engineering software (e.g., RS2, RSPile). This is not a simple web app, it is a distributed, multi‑service AI system spanning cloud and local execution environments.
You will work on core backend services, AI orchestration infrastructure, and desktop‑to‑cloud agent systems that power both “Ask” and “Agent” modes of RSInsight.
This role is ideal for someone who enjoys building production AI systems, distributed services, and clean developer infrastructure.
This is a vacant role withexpectedtotalcompensationof$100,000 - $130,000 CAD
What You’ll Work On
- Design, build, and maintain backend services (FastAPI, Python) deployed on AWS ECS (Fargate)
- Develop and evolve AI agent runtimes that support:
- Context management
- Streaming responses (SSE/WebSockets)
- Build and maintain cloud‑to‑desktop orchestration systems (Electron + local MCP servers)
- Improve performance, reliability, and observability across microservices
- Work on LLM integrations (OpenAI, multi‑model support, token management strategies)
- Build and maintain RAG pipelines (vector DBs, reranking, summarization strategies)
- Collaborate with frontend engineers (Next.js) and desktop developers (Electron)
- Participate in architecture discussions and technical design reviews
- Help shape the long‑term AI strategy for engineering workflows
Frontend:
- Next.js / React
AI:
- OpenAI APIs, tool calling, structured outputs, agent frameworks
DevOps:
- GitHub Actions, Docker, CI/CD pipelines
Observability:
- Logging, tracing, performance instrumentation
What We’re Looking For
Must‑Have
- 2+ years of professional backend or full‑stack experience
- Experience building and deploying production services
- Familiarity with REST APIs and async systems
- Strong problem‑solving skills and ownership mindset
Nice‑to‑Have
- Experience with AI/LLM systems in production
- Experience with agent frameworks or tool‑calling systems
- Familiarity with AWS ECS / containerized deployments
- Experience with vector databases or RAG systems
- Experience building Electron or desktop integrations
- Understanding of token budgeting / context management strategies
What Success Looks Like?
- You can independently ship features across backend services
- You understand how our AI agent runtime works end‑to‑end
- You help improve reliability, performance, and scalability
- You contribute meaningfully to architectural decisions
Why This Role Is Unique?
- You’ll work on production AI systems used by thousands of engineers.
- You’ll build real agentic workflows, not just chat wrappers.
- You’ll operate systems that bridge cloud infrastructure and local engineering software.
- You’ll have meaningful ownership and architectural influence.
Note: This recruitment process uses Artificial Intelligence (AI) tools toassistin screening and evaluating applications.
Skills
Don't send a generic resume
Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.
Get started free