Engineering Team Lead – AI Applications (Life Sciences)

Responsibilities Technical Architecture: Own the overall technical architecture of AI applications for the life sciences domain. Lead the design and implementation of complex agentic workflows, multi-agent collaboration mechanisms, and solutions involving LLM fine-tuning or private deployment.

Technical Problem-Solving: Lead the team in addressing critical challenges such as LLM hallucinations, complex biomedical reasoning, and high-precision information extraction. Develop agent planning, tool-use, and reflection mechanisms to improve the accuracy, reliability, and domain relevance of AI-generated outputs.

Engineering Leadership: Lead, mentor, and develop an AI full-stack engineering team. Establish modern development workflows powered by AI-assisted coding tools and continuously improve engineering quality and delivery efficiency.

Cross-functional Collaboration: Work closely with life sciences experts and product managers to translate complex medical and pharmaceutical requirements into practical AI solutions and agent-based applications.

Hands-on Contribution: Remain actively involved in technical design, architecture and code reviews, prompt optimization, and the resolution of complex engineering challenges.

Qualifications At least 5 years of experience in software or full-stack development, including 2 or more years of hands-on experience delivering AI or LLM-powered applications.

Proven experience leading an agile software engineering team.

Strong understanding of the capabilities, limitations, and underlying principles of large language models.

Hands-on experience with agent frameworks such as LangChain, AutoGen, or CrewAI, as well as common agent orchestration patterns.

Proven experience developing, deploying, and optimizing AI-native applications for complex business scenarios.

Strong commitment to code quality, software architecture, and production-grade engineering practices.

Proficiency in Python and at least one statically typed programming language.

Strong knowledge of modern frontend and backend architectures, as well as cloud-native deployment.

An AI-native mindset and the ability to redesign complex workflows using LLMs and agents.

Professional working proficiency in English, with strong written, verbal, and cross-cultural communication skills.