ml engineer for insurance processes

The team develops production-grade, AI-powered solutions for a major US insurance provider, applying generative AI to processes such as underwriting, claims, and customer service.

• Design, develop, and maintain scalable backend services and APIs using Python and FastAPI
• Build and integrate LLM-powered features using OpenAI GPT and Anthropic Claude
• Develop and maintain MCP servers using FastMCP to expose enterprise tools and data to AI agents
• Create and extend Skills and Plugins for business-specific workflows
• Design and implement RAG pipelines, including document ingestion, chunking, embedding, and retrieval strategies
• Build agentic solutions with LLM orchestration frameworks such as LangChain and LangGraph
• Work with vector databases for semantic search and knowledge retrieval
• Implement observability and diagnostics for LLM applications, including tracing, logging, evaluation, token and cost tracking, latency, and quality monitoring
• Own the application lifecycle from development and testing to deployment and production support
• Use AI-assisted development tools such as Claude and Codex while maintaining code quality
• Collaborate with client stakeholders, architects, and business analysts to translate requirements into working solutions
• Ensure solutions meet enterprise standards for security, data privacy, and responsible AI use

• 4+ Years of professional software development experience, focused on Python
• Experience building production REST APIs with FastAPI or a comparable framework
• Hands-on experience integrating LLMs into real applications, including prompt engineering, tool/function calling, and structured outputs
• Practical experience with MCP servers and LLM tool ecosystems, including Skills and Plugins
• Experience designing and implementing RAG pipelines
• Experience building agentic workflows with orchestration frameworks such as LangChain, LangGraph, or LlamaIndex
• Hands-on experience with at least one vector database, such as Pinecone, Weaviate, Qdrant, Chroma, pgvector, or Azure AI Search
• Experience with observability and diagnostics for LLM systems, such as LangSmith, Langfuse, Arize Phoenix, or OpenTelemetry
• Experience deploying and running production applications using Docker, CI/CD, and at least one major cloud platform: AWS, Azure, or GCP
• Daily, confident use of modern development tools, including VS Code and AI coding assistants such as Claude and Codex
• Strong understanding of software engineering best practices, including clean code, testing, code review, and Git
• English at Upper-Intermediate (B2) level or higher, with the ability to communicate directly with US-based stakeholders
• Будет плюсом: Experience in insurance or broader financial services, LLM evaluation techniques, Kubernetes, infrastructure-as-code, data privacy and compliance for PII in regulated industries, asynchronous Python, message queues, event-driven architectures, frontend development with React or Streamlit

• Условий в вакансии нет