M
Senior Agentic AI Engineer
·Israel
On-siteFull-timeAI EngineeringPharmaceuticalsLife SciencesElectronics Manufacturing
Design, prototype, and deliver agentic AI applications for complex scientific and operational workflows in pharmaceutical research and development. Apply large language models, retrieval, tool integration, and workflow orchestration to build reliable, evaluated solutions in partnership with science,
Responsibilities
- Design and prototype agentic AI solutions for scientific and operational workflows
- Develop agents that reason over enterprise knowledge, use scientific tools and data sources, execute multistep tasks, and support human-in-the-loop workflows
- Experiment with and optimize agent design, reasoning, planning, context engineering, retrieval-augmented generation, memory, tool use, and workflow orchestration
- Evaluate models, prompts, retrieval strategies, and agent configurations to improve quality, reliability, latency, and cost
- Deliver solutions from initial prototypes and user demonstrations through validation and production readiness
- Build reusable components with error handling, traceability, evaluation, and safeguards
- Integrate agentic workflows with enterprise platforms, data services, and applications
- Assess emerging foundation-model and agentic-system approaches and apply those with practical value to R&D
Requirements
- Master’s degree or PhD in computer science, artificial intelligence, machine learning, data science, software engineering, or a related quantitative discipline
- At least 3 years of professional or research experience in AI engineering, machine learning, natural language processing, or AI-enabled application development
- Hands-on experience with large language models, generative AI, retrieval-augmented generation, or agentic AI
- Understanding of reasoning, planning, tool use, workflow orchestration, memory, state management, and human-in-the-loop interaction
- Experience with prompt and context engineering, document retrieval, embeddings, structured data integration, and grounding model outputs in trusted sources
- Strong Python programming skills and experience building modular, tested, maintainable software
- Familiarity with APIs, model-serving interfaces, databases, version control, automated testing, containers, and cloud development environments
- Experience evaluating AI systems with quantitative metrics, structured test cases, model comparisons, and user or subject-matter-expert feedback
- Understanding of large language model limitations and failure modes, including controls, fallback mechanisms, and evaluation methods
- Ability to collaborate with scientific, engineering, product, and IT teams and communicate technical concepts clearly
Nice to have
- Experience in pharmaceutical R&D, healthcare, life sciences, or another regulated environment
Benefits
- Inclusive and flexible working culture
- Professional development and career advancement opportunities
- Opportunities to contribute to healthcare and scientific innovation