Ayr designs and manufactures critical power grid equipment including power transformers, distribution transformers, special-purpose transformers, high-voltage circuit breakers, and medium-voltage switchgear. They serve markets such as renewables, data centers, utilities, oil & gas, and industrial sectors. They position themselves as partners in power projects, offering lifecycle support and working to deliver faster than average industry timelines.
Website: https://ayr.energy
About the role
Ayr Energy is looking for software engineers who can help build software platforms that scale indefinitely and connect the entire organization together. You'll work across distributed systems, data pipelines, APIs, and user interfaces to deliver secure, high-quality products that serve the user and not the other way around.
Our integrated model of combining advanced engineering, tight supply-chain control, and exceptional service empowers you to build resilient solutions that restore reliability and control to the operators who keep the world energized.
What you'll do
- Build large-scale, fault-tolerant distributed systems and data pipelines, ensuring reliability, fault tolerance, and performance at scale
- Architect secure integrations connecting internal systems with third-party platforms to automate workflows
- Integrate and orchestrate LLMs into product workflows, with attention to reliability, guardrails, and context management
- Implement data ingestion pipelines to retrieve data from enterprise sources and build secure indexes/search over that data
- Design APIs and user interfaces that power internal search and other enterprise applications
- Instrument systems for observability (latency, error rates, throughput) and drive continuous reliability improvements
- Work closely with teams to understand their bottlenecks and ensure features are delivered effectively with high quality
- Strong proficiency in Python and/or TypeScript/JavaScript
- Perform thorough code reviews for peers, covering interface design, code quality, and testing strategy
Qualifications
- Bachelor's degree in computer science, Math, Sciences, or a related degree
- Hands-on experience with multi-agent architectures, dynamic model routing, or guardrail/safety systems for LLM-based agents
- Experience with enterprise integrations (e.g., Salesforce, Jira, Slack, or internal system APIs)
- Experience working on infrastructure for distributed systems or cloud-native applications, or experience building full-stack applications that span front-end, REST APIs, and application server, or experience training and productionizing machine learning, or information retrieval systems.
- Familiarity with observability tooling (Datadog, CloudWatch) and event-driven or streaming architectures (Kafka)
- Proven ability to design, build, and ship production-ready software, ideally around AI/ML systems (LLM orchestration, RAG pipelines, tool-calling, agent workflows)
- Experience with cloud infrastructure and containerized deployments (Docker/Kubernetes)
- Solid understanding of distributed systems, databases, and system design fundamentals
- Strong algorithmic design skills and first-principles problem-solving
What we offer
- Collaborative work environment
- Challenging problems to solve
- Competitive benefits including medical, dental, and vision
