> Markdown version of [/jobs/ext/3606766-backend-developer-ai-python](https://www.wearedevelopers.com/jobs/ext/3606766-backend-developer-ai-python). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Backend Developer (AI, Python - **Company:** Lorven Technologies Inc - **Location:** United States (Remote available) - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Application Lifecycle Management, Application Performance Management, User Authentication, Automation of Tests, Microsoft Azure, Code Review, Computer Programming, Continuous Integration, Information Leak Prevention, Software Debugging, Github, Python (Programming Language), Key Management, OAuth, Operational Data Store, Performance Tuning, Redis, OpenAI, Prometheus, Search Technologies, Data Streaming, Enterprise Search, Enterprise Data Management, Datadog, Data Logging, Pinecone, Cloud Monitoring, Retrieval-Augmented Generation, Large Language Models, Grafana, Multi-Agent Systems, Llamaindex, Generative AI, AI Coding Agents, Backend, Langfuse — LLM Observability and Analytics Platform, Agentic-AI, Rate Limiting, Fastapi, Build Management, Pgvector, Containerization, Kubernetes, Bicep, Cosmos DB, Azure AKS, Milvus, Claude, Evaluation of Large Language Models, Invoking Functions, Api Design, Restful APIs, Terraform, GPT, Api Management, Docker, Vulnerability Analysis - **Published:** October 7, 2026 - **Apply:** https://www.dice.com/job-detail/314f3e6c-dd99-4b56-824c-7e3cc9c64854 ## About the Role Must have * GenAI experience (primary focus): * 2+ years of hands-on experience building backend services for GenAI applications, with at least one LLM-based solution delivered to production. * Practical experience integrating LLM APIs (Azure OpenAI, OpenAI GPT, Anthropic Claude): tool/function calling, structured outputs, streaming, token and context management. * Hands-on experience with MCP server development (FastMCP preferred). * Experience implementing RAG pipelines and working with vector search (Cosmos DB vector search, Azure AI Search, pgvector or similar). * Experience with LLM orchestration frameworks such as LangChain, LangGraph or LlamaIndex. * Experience with LLM observability and handling of production concerns such as cost, latency, rate limits and provider fallbacks. Engineering: * 5+ years of professional backend development experience with a strong focus on Python. * Solid experience with FastAPI, including async programming, Pydantic and API design. * Practical experience with Microsoft Azure, including AKS, Azure Cosmos DB and Azure Cache for Redis. * Experience with Docker, Kubernetes deployments and CI/CD with GitHub Actions. * Hands-on experience with observability tooling (Azure Monitor, Application Insights, OpenTelemetry, Prometheus, Grafana). * Good understanding of scalable system design: caching, rate limiting, retries, idempotency and horizontal scaling. * Daily, confident use of VS Code and AI coding assistants such as Claude and Codex. * Upper-Intermediate (B2) or higher English, with the ability to communicate directly with US-based stakeholders. Nice to have * Experience building GenAI solutions in insurance or financial services. * Experience with Azure AI Foundry, Azure AI Search or Azure API Management as an AI gateway. * Experience with multi-agent architectures and LLM evaluation pipelines. * Infrastructure-as-code (Terraform, Bicep). * Authentication and authorization with Entra ID, OAuth 2.0 and managed identities. * Familiarity with compliance requirements for handling PII in regulated industries. ## Description * We are seeking a hands-on GenAI Engineer to join a team developing production-grade, AI-powered solutions for a major US insurance provider. * Designed and developed an enterprise-grade Generative AI platform using Python, FastAPI, and FastMCP to automate recruitment workflows and provide intelligent candidate insights. Built scalable, production-ready APIs that integrated with OpenAI GPT and Anthropic Claude models for candidate screening, resume analysis, job matching, and automated recruiter assistance. * Implemented RAG (Retrieval-Augmented Generation) pipelines using vector databases such as Pinecone/Milvus to provide context-aware responses from enterprise knowledge repositories. Developed AI Agents and custom plugins/skills to automate candidate engagement, interview scheduling, talent recommendations, and workflow orchestration. * Owned the complete application lifecycle, including architecture design, API development, deployment, monitoring, observability, logging, and performance optimization. Leveraged AI-assisted development tools such as Claude, Codex, and VS Code to accelerate development, debugging, code reviews, and delivery. Responsibilities * Design and build backend services that power GenAI applications, integrating Azure OpenAI, OpenAI GPT and Anthropic Claude models. * Develop and maintain MCP servers using FastMCP to securely expose enterprise data, systems and tools to AI agents. * Build RAG and agent orchestration services, including retrieval, context assembly and tool execution, using frameworks such as LangChain or LangGraph. * Use Azure Cosmos DB for both operational data and vector search, with attention to partitioning, RU efficiency and consistency. * Implement caching with Azure Cache for Redis, including LLM response caching, semantic caching and conversation/session state. * Build scalable, high-performance REST APIs with Python and FastAPI, handling streaming responses, rate limits, retries and cost controls for LLM providers. * Containerize services with Docker and deploy and operate them on Azure Kubernetes Service (AKS). * Build and maintain CI/CD pipelines using GitHub Actions, including automated testing, LLM evaluations and security scanning. * Implement monitoring and observability for both services and LLM behavior: tracing of LLM and tool calls, token and cost tracking, latency, error rates and quality metrics (Azure Monitor, Application Insights, OpenTelemetry, Langfuse or similar). * Apply enterprise security practices: secrets management, managed identities, secure MCP tool exposure and protection against prompt injection and data leakage. * Own services end to end: design, implementation, deployment, production support and incident troubleshooting. * Use AI-assisted development tools (Claude, Codex) as a core part of the daily engineering workflow.