Software Engineering – AI Agent

We are seeking a Senior AI Agent Engineer to build AI applications connecting LLMs with enterprise systems, laboratory software, and scientific instruments. This back-end-focused individual contributor will own architecture, deployment, and operation using Python and TypeScript/Node.js, RAG, and secure agent orchestration. This is an applied software engineering role, not a model research position.

• →Design and deliver AI agent applications, back-end services, and APIs using Python and TypeScript/Node.js.
• →Build agent runtimes with prompt and context management, tool calling, persistent state, recovery and human approval.
• →Develop and optimize RAG pipelines, including ingestion, embeddings, vector/hybrid search, reranking, and source-grounded responses.
• →Integrate approved cloud or local model APIs with enterprise or laboratory systems; build reusable MCP clients and servers.
• →Own production quality through testing, CI/CD, access controls, prompt-injection defenses, and monitoring of accuracy, latency, cost, and failures.
• →Lead architecture and delivery decisions, mentor engineers, collaborate across product, science, UX, quality, and support teams, and support AI interfaces when needed.

• Bachelor’s degree or above in computer science, software engineering, AI, automation, data science, or a related technical field.
• 5+ years of software engineering experience, with production development in both Python and TypeScript/Node.js and strong foundations in asynchronous programming, API design, testing and debugging.
• Hands-on delivery of LLM applications or agents using cloud or local model APIs and a relevant framework or SDK, such as LangGraph, LangChain, Semantic Kernel, or LlamaIndex.
• Practical end-to-end RAG experience and proficiency with at least one vector database or search platform, including retrieval evaluation, metadata filtering, and relevance troubleshooting.
• Experience with prompt/context engineering, structured outputs, tool orchestration, state management and failure recovery; sound judgment on when deterministic workflows are preferable.
• Strong API, database, and authentication integration skills; familiarity with MCP, Docker, Linux, CI/CD, observability, least-privilege access, and secure handling of model outputs.
• Ability to own architecture and production delivery, collaborate across functions, communicate effectively in English, and support AI interfaces when needed.

• Advanced agent-platform experience: long-running or multi-agent workflows, reusable MCP services, evaluation pipelines, and operational recovery.
• Local inference or hybrid cloud/local deployments, advanced retrieval optimization, and scalable services using technologies such as FastAPI, Redis, queues, Kubernetes, or OpenTelemetry.
• Scientific software, laboratory automation, instrument integration, LIMS/CDS, regulated workflows, or integration with .NET/C# applications.
• Angular, Electron, or React for agent workspaces and approval interfaces; enterprise identity and Responsible AI practices.