?What You'll Do Design, build, and own backend services and infrastructure for our GenAI applications – scalable, resilient, production-grade systems running on AWS. Build the APIs, data pipelines, and backend integrations that power advanced AI capabilities, including knowledge bases, embeddings, LLM orchestration, agent workflows, and evaluation frameworks, with attention to performance, scalability, and security. Lead complex design efforts – driving architecture discussions, design reviews, and technical decisions for significant areas of the system. Collaborate closely with product, data science, and other engineering teams to translate business needs into robust backend solutions that enable AI-agent use cases. Raise the engineering bar through code reviews, mentoring less experienced engineers, and championing best practices in quality, observability, and operational excellence. Take ownership of production health, including monitoring, alerting, troubleshooting, and continuously improving system reliability.
Position Intro:
Earnix is the first AI company purpose-built for insurance decisioning, providing the industry with the intelligence, governance, and decisioning agility to drive profitable growth, improve resilience, and operate with speed and precision in a rapidly changing risk environment. A trusted provider of production-grade AI and decisioning technology, Earnix builds on more than 25 years of experience in artificial intelligence risk, pricing, rating, analytics, and decisioning. Earnix brings vertical AI into the workflows and decisions that shape insurance performance across insurers pricing, underwriting, claims, customer engagement, retention, and other insurers high-value insurance moments. Earnixs AIOS enables insurers to orchestrate intelligence across the insurance decision lifecycle and drive governed, Real-Time decisions that deliver measurable business outcomes. Earnix is headquartered in Boston, MA and has been innovating for insurers and banks since 2001 with customers in over 35 countries across six continents and offices in the Americas, Europe, Asia Pacific, and Israel.
You'll do it using: 5+ years of backend engineering experience building and operating production systems at scale, with a strong sense of ownership from design through deployment and operations. Deep expertise in microservices architecture, API design, and distributed systems, with cloud-native design experience on AWS (or GCP/Azure) using Kubernetes and Helm. Proficiency in Python for building scalable backend services, with a focus on clean, production-grade code and seamless integration of AI components. Hands-on experience integrating Generative AI into backend systems, including LLMs, knowledge bases, and agent frameworks, plus familiarity with tooling such as AWS Bedrock, LangChain/LangGraph and vector databases. Solid experience with data and messaging technologies – SQL/NoSQL databases, caching layers, and message brokers such as PostgreSQL, Redis, Kafka, RabbitMQ, and Elasticsearch. Strong command of observability practices, with hands-on experience in tools such as Prom
