At Mandrake Bioworks, we're building a new kind of biotech company. One where plants are programmable systems, and AI is the design engine. Our mission is to reimagine the process of trait discovery and biological design using AI-first methods and multi-omics data. From climate-resilient crops to plants engineered for high-value compound production, our work sits at the intersection of deep-tech, biology, and planetary need. This is not just about applying machine learning to biology. It’s about building novel infrastructure and models that don't exist yet, starting from first principles. You’ll be collaborating closely with a multidisciplinary team of: Some of the best Plant biotechnologists & geneticists in the country Experienced operators in climate, biotech, and venture-backed deep-tech AI/ML engineers and bioinformaticians who’ve built production-grade models and platforms at scale This is a rare chance to work at the confluence of real-world biological complexity and cutting-edge AI research with a team deeply committed to impact and excellence. You’ll work as a founding member of our AI team, helping architect systems that bring plant biology into the machine learning era. Responsibilities include: Build and optimize data pipelines that integrate large-scale, heterogeneous datasets from multiple sources Develop custom LLM workflows and domain-specific foundation models to extract actionable insights Fine-tune open-source language and graph transformer models for NER, entity resolution, and relationship extraction Design systems that blend prompt-engineering, retrieval augmentation, and probabilistic reasoning to manage high-noise data environments Translate cutting-edge research into modular, production-ready AI tools using real-world datasets We’re Looking for someone who’s obsessed with systems-level thinking, loves working at the edge of what's known, and is unafraid of complexity. Must-Haves: Strong experience with Python, PyTorch/TensorFlow, and deep learning fundamentals Familiarity with LLMs, Transformers, or graph-based models Hands-on experience building robust data pipelines and handling multi-modal datasets Passion for biology and willingness to dive deep into genomic/omics datasets Perpetually curious, grounded in first-principles thinking, and unafraid to question how things are done Comfortable with ambiguity, fast learning, and ownership-you care more about solving the problem than defending a method Bonus Points: Experience with scientific literature parsing, NER, or bio-NLP Familiarity with omics standards (e.g., FASTA, VCF, GTF, KEGG, GO terms) Exposure to working with large-scale biological or medical datasets Interest in systems biology, synthetic biology, or computational genomics What You’ll Get: Monthly stipend + pathway to full-time offer Ownership of core systems in a high-ambition deep-tech startup Mentorship from leaders across AI, biology, and engineering Opportunity to co-author papers, build open-source tools, and ship real infrastructure Front row seat into how a deep-tech moonshot is scaled towards a global impact Biology today is where the internet was in the early 2000s - fragmented, messy, and yet full of potential. At Mandrake, we’re building the models, abstractions, and infrastructure to make biology programmable at scale. Your work won’t sit in a research repo - it’ll directly power biological discoveries, product pipelines, and planetary-scale impact. Show more Show less