LLM Agent Engineer

About the Role

We are seeking a highly experienced LLM Agent Engineer to design, develop, and deploy specialized Large Language Model (LLM) agents for advanced applications in single-cell analytics and omics data. You will play a key role in building intelligent personas using the LangChain framework to bridge complex biological datasets with advanced AI capabilities.

This is a unique opportunity to contribute to cutting-edge scientific research through applied AI.

Key Responsibilities

• Design and implement LLM agents and personas using LangChain and other LLM frameworks.
• Build intelligent pipelines for biological data exploration and scientific analysis.
• Develop, fine-tune, and adapt LLMs for domain-specific tasks in genomics, transcriptomics, proteomics, etc.
• Integrate LLM agents with existing bioinformatics workflows and scientific toolkits.
• Collaborate with frontend and backend teams to develop RESTful APIs that connect LLM agents to applications.
• Ensure high-quality, scalable code for both experimental prototypes and production-level agents.

Must-Have Requirements

• 7+ years of experience as a Data Engineer or in related roles.
• 5+ years of hands-on experience with:
  • LLMs and agent architectures
  • Python, with strong use of LangChain, Hugging Face, PyTorch or TensorFlow
  • OpenAI APIs and LLM tuning techniques
• Deep familiarity with LangChain concepts:
  • Prompt templates, memory, tools, and chains
  • Agent architectures and middleware logic
• Solid understanding of omics data formats and bioinformatics workflows
• Experience with single-cell analytics or scientific data pipelines
• Strong ability to preprocess, clean, and structure complex datasets for LLM consumption
• Experience building and documenting RESTful APIs to serve LLM agents

Nice to Have

• PhD or MSc in Bioinformatics, Computational Biology, or related field
• Hands-on experience with:
  • Popular omics toolkits (e.g., Scanpy, Seurat, Bioconductor)
  • Scientific computing frameworks (e.g., NumPy, SciPy, Pandas, scikit-learn)
  • Deployment of models in production (Docker, Kubernetes, cloud services)

Preferred Regions

Candidates must reside in one of the following EMEA or Eastern Europe & Central Asia countries:

• Europe: Poland, Ukraine, Romania, Bulgaria, Hungary, Czech Republic, Slovakia, Serbia, Croatia, Georgia, Armenia, Moldova, etc.
• Central Asia: Kazakhstan, Kyrgyzstan, Uzbekistan, Tajikistan
• Middle East: UAE, Israel, Jordan, Turkey, etc.

Why Join Us?

• Work with world-class researchers and engineers on a pioneering AI product
• Remote-first culture with flexibility and autonomy
• Opportunity to push the boundaries of AI in the life sciences domain