AI/LLM Engineer (m/f/n)

Task Description

• Technical design and conceptualization of JARVIS components
• Drafting of technical concepts and implementation plans covering agentic process/pipeline design, interactions with the Apollo AI gateway, tool and Model Context Protocol (MCP) boundaries, operational constraints, and quality-gate validation approaches.
• Technical programming of LLM-enabled Python services
• Independent execution of programming tasks to develop agentic workflows utilizing BI's Apollo AI gateway.
• Technical integration of AI coding-assistant tooling, asynchronous/streaming processing, OAuth2 authentication, configuration handling, and run-mode management.
• Development of agentic workflow architectures
• Technical programming and structuring of core workflow components, including tool invocation, function calling, Model Context Protocol (MCP) integration, state handling, and error handling.
• Drafting and technical configuration of multi-stage pipeline orchestration models (deliver ? expert ? review ? quality-gate).
• Technical development of web interaction interfaces
• Execution of programming tasks to create frontend interaction surfaces for JARVIS workflows, specifically utilizing Streamlit.
• Technical implementation of input forms, result and status views, feedback capture mechanisms, and usage/budget displays.
• Technical implementation of observability and governance mechanisms
• Drafting and programming of evaluation and guardrail mechanisms for agentic applications.
• Technical configuration of cost and token tracking, hard budget caps, latency tracking, and output-quality monitoring gates based on defined use-case parameters.
• Containerization and deployment configuration
• Execution of containerization tasks utilizing Docker and OpenShift (Boehringer's internal OpenDevStack/EDP platform).
• Technical drafting of Kubernetes/OpenShift configurations, CI/CD pipeline definitions, and SSO-gated environment parameters.
• Execution of technical quality assurance and testing
• Independent execution of testing protocols on implemented backend, workflow, and interaction components.
• Technical expansion of existing automated suites including unit tests, integration tests, and browser-based E2E scenarios.
• Drafting of structured defect reports documenting identified high-severity anomalies for handover to BI project governance.
• Creation of technical documentation and handover reports
• Drafting of comprehensive technical documentation covering architecture decisions, output results, operational monitoring setup, and known limitations.
• Creation of a finalized project report consolidating all implemented JARVIS components and evaluating the extracted meta-patterns.

Requirements

• 5+ years of professional experience in Software Engineering / AI Development, including 3+ years hands-on experience with LLMs, RAG and/or agentic AI systems.
• Proven experience delivering at least one production-grade LLM, RAG or agentic AI application.
• Strong Python skills and practical experience with prompt engineering, RAG, agentic workflows and LLM/tool integrations.
• Experience with agent orchestration and MCP integrations; knowledge of frameworks such as LangGraph or CrewAI is beneficial.
• Hands-on experience with GitHub Copilot or comparable AI coding tools.
• Experience with Docker, Kubernetes/OpenShift and CI/CD pipelines.
• Ability to independently make architecture and implementation decisions in a fast-moving MVP environment with limited guidance.
• Fluent English is mandatory.

Nice-to-have:

• Experience in pharma, healthcare or another regulated/data-sensitive environment, including familiarity with topics such as GDPR, EU AI Act or GxP.
• Knowledge of Responsible AI / LLM security practices, e.g. OWASP guidance and bias/fairness evaluation.
• Experience with Streamlit, React/TypeScript, Dify or local LLM deployment.
• Experience working in international corporate environments and/or fast-paced startup or scale-up settings.
• Open-source AI contributions or a portfolio of successfully shipped AI solutions.