What are the responsibilities and job description for the Artificial Intelligence Engineer position at Stelvio Inc.?
AI Backend Engineer (LLMs / Distributed Systems)
Austin, TX | Hybrid | No C2C or Sponsorship
I’m working closely with a fast-moving AI team building production-grade systems around large language models, focused on moving beyond demos into fully deployed, scalable products.
This is a role for engineers who enjoy operating at the intersection of backend systems and applied AI — where performance, reliability, and real-world usage actually matter.
What you’ll be working on
- Designing and scaling backend services powering AI-driven applications (TypeScript / Node / Python)
- Building real-time and event-driven systems that integrate with modern LLMs
- Implementing streaming architectures, structured outputs, and tool/function-calling workflows
- Working closely with product and applied AI teams to take ideas from concept → production
- Shipping end-to-end features including system design, deployment, and reliability
- Improving observability (metrics, logs, tracing) alongside cost and latency optimization
What they’re looking for
- Strong backend engineering fundamentals with a bias toward shipping and iteration
- Experience building and deploying applications powered by modern LLM APIs
- Hands-on work with structured outputs, streaming responses, and model orchestration
- Comfort operating in ambiguous environments — able to self-direct and execute
- Solid understanding of distributed systems, real-time processing, and production reliability
Strong experience signals
- Experience across multiple model providers (e.g. OpenAI, Anthropic, Google, open-source models)
- Familiarity with orchestration frameworks (e.g. LangChain, LangGraph) or similar tooling
- Experience optimizing model usage (latency, cost, evals, prompt workflows)
- Background working with modern backend stacks (TypeScript/Node.js, PostgreSQL, Redis, queueing systems)
- Exposure to cloud environments (GCP preferred, AWS/Azure also relevant)
Working environment
- Early-stage, high-ownership team where engineers shape both product and technical direction
- Strong engineering culture with a focus on building and shipping quickly
- Fully in-person environment to enable tight collaboration and fast iteration
- Downtown Austin location
If you’re already building with modern AI systems and want to work on products where the complexity goes beyond surface-level integrations - this is worth exploring.
Feel free to reach out for more context.