Описание вакансии
Responsibilities:
- Identify and implement practical opportunities to embed AI into backend services and business workflows to improve efficiency, accuracy, or decision support.
- Design and build production-ready AI-enabled services combining application logic, APIs, and AI models to support real customer and operational use cases.
- Integrate LLMs, ML models, and external AI services into existing systems using strong engineering patterns for reliability, observability, and maintainability.
- Build workflows that use AI in a bounded, auditable way, with clear fallback behavior, evaluation, and human review where appropriate.
- Partner with product, design, data, and operational teams to turn workflow pain points into scalable software solutions with measurable impact.
- Lead software development: design, develop, test, and deploy scalable and maintainable software applications using Spring Boot, Java, React, and cloud technologies.
- Collaborate with product managers, designers, and cross-functional teams to architect robust and scalable solutions meeting business requirements.
- Provide input into the technical direction of the team and product.
- Leverage experience with cloud platforms (AWS, Azure, Google Cloud) to design cloud-native applications optimized for scalability, reliability, and cost-efficiency.
- Conduct thorough code reviews and mentor junior and mid-level engineers.
- Work closely with product and design teams to define requirements and deliver timely solutions.
- Monitor and optimize application performance, identifying bottlenecks and implementing improvements across frontend (React) and backend (Java/Spring Boot).
- Participate in Agile development processes including sprint planning, daily standups, retrospectives, and backlog grooming.
- Continuously research and apply emerging technologies and industry best practices to improve development process and product quality.
Requirements:
- 8+ years of professional software engineering experience building scalable distributed systems with a track record of driving technical direction and architecture decisions.
- Mastery of Java, Spring Boot, and Python for developing secure, high-throughput, cloud-native backend systems (AWS, Azure, or GCP).
- 2–3+ years of hands-on experience designing, shipping, and maintaining production AI-enabled or AI-native applications combining LLMs, core application logic, and business workflows.
- Practical experience with orchestration frameworks (e.g., LangChain, LangGraph, LlamaIndex, CrewAI) and understanding of RAG, tool calling, prompt engineering, context/state management, and human-in-the-loop patterns.
- Strong background in distributed systems, event-driven architectures, asynchronous processing, and messaging platforms (e.g., Kafka).
- Proven experience implementing enterprise AI guardrails including real-time observability, latency/cost monitoring, automated evaluation pipelines, and robust fallback mechanisms.
- Excellent cross-functional communication skills to bridge Engineering, Product, Design, and Operations.
- Preferred: experience building autonomous, multi-step agentic AI systems, healthcare IT or fintech domain expertise, hands-on experience with vector databases, semantic search, enterprise knowledge graphs, advanced ML tooling (PyTorch, Hugging Face Transformers), and leadership experience as Founding Engineer or Principal Architect.
Benefits:
- Competitive and fair compensation with pay bands based on geographic zones.
- Variable pay and robust benefits package.
- Remote work based in the United States.
- Wellness and childcare subsidies (Costa Rica).
- Discounts on work-from-home basics and health/fitness resources.
Additional Information:
- Tebra is an equal opportunity employer.
- Interviews are conducted via official channels only.
- Application via official portal only.