Senior Software Engineer

Requirements: Ideally, 5+ years of software engineering experience, including substantial experience building production systems. Strong experience at an early-stage or rapidly scaling technology startup, including helping take products from initial launch to meaningful scale. Proven ability to own production services end-to-end, from architecture and implementation through deployment, infrastructure, monitoring, and ongoing operations. Strong Python skills and deep backend engineering knowledge. Strong understanding of distributed systems, asynchronous processing, queues, workers, concurrency, failure handling, and reliability. Experience designing and operating systems on AWS.Experience building production APIs and complex third-party integrations. Experience building AI-powered applications with modern LLMs; familiarity with frameworks such as LangChain or LangGraph, or comparable orchestration systems. Experience with retrieval systems, embeddings, vector databases, or platforms such as Pinecone. Practical understanding of prompt engineering, structured outputs, evaluations, guardrails, context management, and production LLM reliability. Strong SQL skills and relational database fundamentals. Strong architectural judgment, including knowing when to keep systems simple and when additional infrastructure is warranted. Comfort with incomplete requirements, changing priorities, and making decisions independently. Curiosity about and hands-on experimentation with new AI and developer tools, models, frameworks, and infrastructure. Experience with document intelligence, OCR, multimodal systems, or LLM-based extraction pipelines is highly valuable. Experience with voice AI agents or real-time AI systems is a plus.

Responsibilities: Own critical products and services across architecture, development, deployment, infrastructure, monitoring, and scaling. Design and operate distributed systems and asynchronous pipelines that process large volumes of healthcare data and workflows. Build production AI systems involving LLMs, agents, retrieval, document intelligence, and custom pipelines. Develop infrastructure for LLM-powered applications, including evaluation, prompting, tool use, guardrails, observability, and reliability. Create document-processing and LLM/OCR pipelines that convert complex healthcare documents into structured, actionable data. Design high-performance APIs and integrations with healthcare systems, vendors, and third-party platforms. Improve system reliability as workloads grow substantially. Make pragmatic architecture decisions that balance development speed with long-term scalability. Experiment with AI models, frameworks, coding tools, and infrastructure, assessing their effectiveness in production. Debug complex issues spanning application code, distributed workers, databases, infrastructure, networking, and external systems. Collaborate with product, operations, customers, and engineers to turn real-world workflow challenges into scalable software. Establish technical patterns, infrastructure, and engineering practices that support CuraFis growth.

Technologies: AIAI AgentsAWSBackendSupportLLMPythonSQLCloudMore: