Senior Generative AI & Agent Systems Software Engineer (Remote)

Further Details

This remote Software Engineer position at Invox Medical focuses on developing advanced Generative AI and Agent Systems for the healthcare industry. The role involves designing and implementing the complete runtime of agents, from initial architecture to production deployment, with a strong emphasis on reliability, measurability, and maintainability. Successful candidates will leverage their expertise in Python and TypeScript to build sophisticated agentic workflows that enhance clinical efficiency and patient outcomes. Key responsibilities include architecting agent runtimes with LangGraph, managing state and memory, ensuring secure tool usage, implementing Retrieval-Augmented Generation (RAG) strategies for clinical knowledge, and establishing comprehensive observability and evaluation frameworks. This role is ideal for experienced engineers who are passionate about applying rigorous software engineering practices to the dynamic field of AI in healthcare, contributing to products that significantly impact the daily lives of medical professionals.

Senior Generative AI & Agent Systems Software Engineer (Remote)

Invox Medical is actively seeking a talented Senior Software Engineer with a specialization in Generative AI and Agent Systems for a fully remote position based in Euskadi, Spain. This role is crucial for developing innovative voice and AI products within the healthcare sector, aiming to enhance patient care by optimizing healthcare professionals' time. The company is expanding its platform with agent systems capable of sophisticated context understanding, tool utilization, and end-to-end clinical workflow execution.

The ideal candidate will possess a strong background in designing and building reliable, measurable, and maintainable agents for production environments. This involves architecting the complete agent runtime, from state management and memory to tool integration and robust error handling. You will apply rigorous software engineering principles to complex, non-deterministic AI systems, ensuring the highest standards of quality, security, and traceability in a critical industry.

• Job Title: Senior Generative AI & Agent Systems Software Engineer
• Location: Remote (Euskadi, Spain)
• Company: Invox Medical
• Key Technologies: Generative AI, Agent Systems, LangGraph, Python, TypeScript, AWS
• Focus: Healthcare Technology, Clinical Workflow Automation
• Required Experience: Proven experience building production-grade agents and multi-step workflows
• Qualifications: Bachelor's degree or higher in a relevant field

Skills

• Experience building production agents with multi-step workflows, routing, tool use, persistent state, and explicit failure handling
• Proficiency in LangGraph for architecting agent runtimes (StateGraphs, nodes, edges, subgraphs, checkpoints, interrupts, resumption)
• Strong asynchronous Python skills, including typing, testing, and service design
• Practical TypeScript experience for developing integrations and APIs
• Experience with production engineering practices: APIs, queues, events, concurrency, idempotency, security, CI/CD, Docker, and AWS deployments
• Experience with LLM/agent observability and evaluation tools (e.g., OpenTelemetry, Arize Phoenix, Langfuse, LangSmith, Datadog, Ragas, DeepEval)
• Expertise in tool calling and structured outputs, including schema design, model response validation, and error handling
• Applied RAG knowledge: chunking, embeddings, hybrid search, reranking, security filters, and retrieval evaluation
• Understanding of traceability, privacy, reproducibility, and safety in AI-assisted decisions

Duties and Responsibilities:

• Design and build agent runtimes using LangGraph, including nodes, routing, loops, parallelism, streaming, interrupts, and subgraphs
• Model typed and persistent state, session memory, long-term memory, checkpointers, execution resumption, idempotency, timeouts, retries, and cost limits
• Design tool contracts, structured outputs, and tool calling mechanisms; integrate APIs and clinical sources with permissions, validation, sandboxing, and human-in-the-loop intervention
• Build hybrid retrieval, reranking, tenant filters, Graph-RAG, and grounding strategies over medical knowledge, utilizing vector databases and knowledge graphs
• Select and combine models based on quality, latency, cost, privacy, and availability; work with providers like AWS Bedrock and other model APIs without architectural coupling
• Instrument every execution for decision-making, tool usage, token count, cost, latency, and errors; create datasets and regression evaluations for medical fidelity, groundedness, safety, and tool use quality
• Implement the core logic in Python and platform integrations in TypeScript, deploying robust services on AWS, and potentially in containerized or on-premise environments

How to apply

• Step 1: Visit the Application Portal Navigate to the official application link provided for this position.
• Step 2: Review Job Details Thoroughly read the job description, responsibilities, and required qualifications to ensure your profile aligns with the role's demands.
• Step 3: Prepare Your Application Documents Ensure you have an up-to-date Curriculum Vitae (CV) detailing your relevant experience, particularly in Generative AI, Agent Systems, Python, TypeScript, and production deployments.
• Step 4: Complete the Online Application Form Fill out all required fields accurately on the application form. This may include personal details, educational background, and professional experience.
• Step 5: Submit Your Application Click the submit button to send your application for review.
• Important Notes:
  • This is a 100% remote position.
  • The closing date for applications is December 18, 2026.
  • Ensure your application highlights your experience with LangGraph, tool calling, RAG, and production engineering in AI systems.