Design semantically precise and biologically grounded prompts for large AI models used in genomic inference, synthesis design, and ancestral modeling. You’ll work closely with researchers to translate high-level questions into effective AI inputs—driving sequence generation, trait mapping, or regulatory logic extrapolation. The role requires domain fluency and a nuanced understanding of how language models encode and express biological reasoning. Your prompts will shape everything from foundational research to applied bioengineering.

Design large-scale, multi-agent AI ecosystems capable of coordinating complex genomic reasoning tasks across models, data centers, or research labs. You’ll build infrastructure that enables shared memory, federated learning, and adaptive role assignment across a network of intelligent systems. These agents might specialize in different forms of genomic prediction, bio-design, or historical synthesis—but must work in unison. Your architecture will define how AI collaborates across space and time.

Shape the protocols by which AI agents collaborate on genomic analysis, synthetic design, and evolutionary reconstruction. You’ll create and refine communication patterns between models that specialize in different domains—sequence prediction, regulatory mapping, metabolic modeling—to ensure coherence and shared goals. This role bridges technical coordination and emergent reasoning among distributed systems. Success depends on both systems thinking and an intuitive grasp of how AI “understands” biology.

Coordinate a network of specialized AI agents that collectively analyze, design, or simulate biological systems. You’ll manage workflows, resolve conflicts between agent outputs, and maintain shared state as tasks evolve. These agents may focus on different data types or biological functions but must collaborate to achieve cohesive outcomes. This is a high-level systems role focused on orchestrating synthetic intelligence across diverse objectives.

Build and scale the infrastructure that powers genomic AI research, synthetic design, and data exploration. You’ll develop APIs, processing engines, model-serving layers, and collaborative tools that enable scientists and AI systems to work fluidly together. The platform must handle large, diverse, and highly specialized data with robustness and speed. Your engineering will underpin some of the most advanced AI-biology interactions ever attempted.

Develop AI systems that achieve deep expertise in specific subdomains of biology, such as gene regulation, sequence reconstruction, metabolic modeling, or protein folding. You’ll curate data, design learning objectives, and supervise model evolution toward high performance in well-bounded tasks. Vertical AIs serve as trusted assistants in complex research workflows. Your goal is not generality, but precision and mastery.

Investigate and model the elements that control gene expression—enhancers, silencers, promoters, and boundary elements—and how they can be interpreted or designed by AI. You’ll guide systems that map regulatory logic across time, context, and cell states. Your role is key to ensuring synthetic constructs express genes in a controlled, predictable manner. This is where biology meets logic architecture.

Push the limits of performance, efficiency, and stability for AI models operating on large-scale biological data. You’ll work on pruning, distillation, quantization, and parallelization to ensure fast, reliable performance. Optimization is not just about speed—it’s also about keeping outputs accurate under tighter computational or temporal constraints. Your work enables real-time feedback in bio-design systems and scalable inference across massive genomic libraries.

Develop novel probabilistic frameworks that help AI reason under biological uncertainty—especially in cases of incomplete data, conflicting signals, or speculative design. You’ll use Bayesian modeling, stochastic processes, and dynamic inference systems to help AI balance exploration with constraint. These tools allow models to suggest hypotheses, not just answers. Your work powers risk-aware discovery in both synthetic and evolutionary biology.

Work with AI-controlled bio-integrated systems—ranging from microfluidic lab automation to bio-inspired actuators—to physically manifest the outcomes of synthetic biology designs. You’ll develop training loops and feedback models that teach embodied agents how to perform complex protocols derived from genetic blueprints. This includes kinetic training, environmental adaptation, and iterative physical learning from biological constraints. The role combines robotics, molecular biology, and AI training systems.

Develop training protocols for robotic systems designed to execute physical workflows in genomics, such as lab automation, sample preparation, or synthetic assembly. These systems may act on AI guidance but require physical calibration to biological constraints. You’ll help robotic platforms learn precision, rhythm, and responsiveness in bio-contexts. This role blends mechanical intelligence with life science tactility.

Create expansive, high-fidelity synthetic datasets for use in training genomic AI systems—ranging from realistic DNA sequences to simulated phenotypic traits. Your pipelines must balance realism with experimental controllability, enabling safe exploration of new hypotheses. You’ll work closely with biologists and ML researchers to define the data the models need. This role shapes the entire knowledge frontier for synthetic biology AI.

Build intelligent pipelines that interconnect fragmented datasets—historic genomic records, expression assays, design logs, and environmental metadata—into structured, context-rich formats for AI consumption. You’ll ensure each data element carries the right temporal, biological, and methodological context to support robust training and inference. Your systems help models make accurate inferences even from incomplete or heterogeneous inputs. This work is critical to preventing model misinterpretation due to data mismatches.

Develop statistical and generative techniques to smooth over noisy, gapped, or uncertain biological data. This includes interpolating degraded genomic sequences, normalizing synthetic readouts, and aligning mismatched annotations across experiments. Your work allows AI models to train on datasets that more closely resemble the true structure of biological reality. Smoothing doesn’t just clean data—it enables pattern recognition in places humans and machines might otherwise fail to look.

Support model training by developing finely curated biological annotations—ranging from genomic features to synthetic construct outcomes. You’ll collaborate with scientists to ensure accuracy in trait labels, expression patterns, and structural motifs. High-resolution, context-aware annotation enables better generalization and reliability in AI-driven predictions. This role is foundational to supervised learning pipelines in both ancient genomics and synthetic applications.

Design genomic alignment protocols across a wide range of biological datasets—ancient, synthetic, and modern. You’ll help AI systems identify conserved elements, novel divergences, and functional equivalencies across species boundaries. These insights guide synthetic genome design and deepen our understanding of evolutionary logic. Precision, scale, and interpretability are all key to success in this role.

Lead efforts to construct and interpret pangenomic models that describe species-wide genetic variation across populations and time. You’ll help AI systems generalize across diverse genomic backgrounds, uncover underrepresented alleles, and suggest robust design templates. Your work informs everything from trait resilience to cross-lineage engineering. This is a cornerstone role in systems-scale genomics.

Lead long-term AI research into the patterns and pressures that shaped genomic evolution, with an eye toward designing new biology informed by the past. You’ll oversee cross-functional teams working on AI-assisted reconstruction, comparative analysis, and systems synthesis. Your insights feed directly into synthetic genome development, repair algorithms, and novel trait creation. This role demands deep biological intuition and comfort with abstract reasoning at scale.

Design and interpret phylogenomic frameworks that trace gene histories, infer relationships, and guide AI in making plausible biological extrapolations. Your work supports sequence prediction, trait mapping, and synthetic feasibility. You’ll help AI models understand what “related” means in terms of structure, function, and evolutionary trajectory. This knowledge underpins design logic in both synthetic and comparative contexts.

Analyze variants proposed or identified by AI systems for functional relevance, biological feasibility, and synthetic applicability. You’ll assess how specific changes may affect gene expression, protein structure, or regulatory context. This work blends predictive modeling with interpretive science, often requiring deep domain judgment. Your expertise ensures that variant-level decisions made by AI lead to meaningful insights or stable synthetic constructs.

Use AI models to simulate and analyze metabolic processes—predicting how synthetic organisms might produce, consume, or regulate biochemical products. You’ll work on both naturally observed pathways and AI-designed variants. This includes testing the viability of model-generated networks and identifying bottlenecks or emergent efficiencies. Your findings are critical for designing organisms with practical biofunction.

Apply cutting-edge AI tools to model, simulate, and analyze complex biological systems—such as gene networks, expression pathways, and large-scale genomic datasets. You’ll work with both ancient and synthetic data, identifying patterns that inform design, discovery, and understanding. This role requires strong biological grounding alongside fluency with modeling languages, AI frameworks, and algorithmic reasoning. Your models may drive everything from synthetic enzyme design to ancestral gene reconstruction.

Track and interpret emergent patterns that arise from AI systems trained on complex biological inputs or engaged in open-ended design tasks. You’ll assess whether these behaviors represent creative solutions, system drift, or potential risks. Understanding when an AI has generated a useful new biological hypothesis—or veered into uncharted and unsafe territory—is central to this role. You’ll work closely with model trainers and safety teams to flag and guide emergent reasoning.

Bridge the gap between AI-driven genomic analysis and human understanding by building tools and narratives that explain model logic. Whether the system is predicting regulatory behavior or proposing new gene architectures, you’ll help researchers trace how the AI reached its conclusion. The role combines knowledge of model internals with storytelling and visualization skills. Your output empowers scientists to trust, interrogate, and refine what the AI suggests.

Conduct rigorous evaluations of AI models used in interpreting ancient and synthetic genomic data, with a focus on integrity, reproducibility, and safety. You’ll assess where models may hallucinate, drift from biological feasibility, or reinforce data artifacts. The auditing process includes building interpretability tools and stress-testing against degraded, ambiguous, or oversampled inputs. Your insights will shape how models evolve and remain aligned with both science and regulation.

Build and maintain testing pipelines that verify the stability and robustness of AI systems across biological edge cases, uncertain inputs, and novel synthetic constructs. You’ll simulate adversarial biological data, validate outputs against known benchmarks, and ensure models don’t propagate implausible or unsafe suggestions. In synthetic biology, even subtle model errors can cause cascading system failures—your role is key to preventing them. This work combines formal verification with practical resilience engineering.

Design and formalize alignment strategies that keep AI systems grounded in biological feasibility and ethical research frameworks. You’ll create reward structures, constraint models, and system-level logic to guide AI behavior during exploration, design, and prediction. These mechanics ensure outputs not only “work” computationally but respect boundaries of safety, resource constraints, and scientific relevance. Your contributions will help harmonize AI ambition with real-world biological limits.

Assess the emergent behaviors of AI systems tasked with genomic reasoning, design iteration, or simulated biological responses. You’ll track how models adapt to new inputs, whether they remain consistent across similar prompts, and how they “explain” or justify decisions. The job is part detective, part debugger, and part biologist—rooted in understanding how models express intention and how that expression translates into useful or risky biological action. Your findings will guide future model iterations and safety standards.