Software Engineer (Agentic) in London

About Us

Biographica is on a mission to accelerate the development of more productive, sustainable, nutritious & climate‑resilient food sources. To achieve this, we're building the world’s first ML‑driven target discovery platform for crop gene‑editing.

Target discovery for gene‑editing

While gene‑editing of crops is becoming ever more efficient, identifying which genes to edit and how remains a significant challenge. To overcome this bottleneck, we use cutting‑edge deep learning to accurately and efficiently identify high value genetic targets for crop gene‑editing. Our approach draws inspiration from advancements in the drug discovery space, incorporating transformers, graphs & causal‑ML to build a best‑in‑class discovery platform for plant sciences.

Building agent‑native scientist‑in‑the‑loop discovery

Our next chapter is to productise target discovery so we can deliver deep, traceable discovery projects quickly and in parallel. We believe scientific agents, grounded in Biographica‑curated data and proprietary models, will be key to scaling both the breadth and depth of our analyses. This role will own the orchestration and platform layer that makes agentic workflows reliable, reproducible, and genuinely useful to scientists.

Team

Led by co‑founders Dom (CTO) and Cecy (CEO), we are now a team of 13, including 2 ML engineers, 2 data engineers, 3 bioinformaticians & 2 experimental scientists. We primarily work together in person from our office in Spitalfields, London, 4 days per week. This role will be based in London, with close collaboration across ML, data and scientific product.

What we're looking for

We’re hiring an agentic‑focused software engineer to build out internal agentic frameworks for our discovery product. You will define and implement the operating system that allows scientists to run repeatable, agent‑in‑the‑loop tool‑using workflows while maintaining provenance, traceability and checkpoints.

Your First Priorities Will Be

• Designing and implementing the core orchestration layer for scientist‑in‑the‑loop, agent‑based discovery workflows that plug into our existing stack (Dagster assets, MLFlow model registry, internally curated plant databases).
• Building a robust tool registry and execution framework so agents or scientists can safely call Biographica tools (model inference, dataset retrieval/QC, literature search, bioinformatics workflows, etc.) with clear inputs/outputs.
• Establishing provenance, logging, and evaluation infrastructure so every agent run is reproducible and reviewable by scientists and customers.

Core responsibilities

• Own the architecture and implementation of our agentic workflows (Python‑first) including state management, retries, branching, and human checkpoints.
• Build and maintain a tooling interface layer that standardises how agents call internal services and external APIs, with strong typing, validation, and error handling.
• Implement provenance and traceability: versioned inputs, prompt/tool versions, dataset/model pointers, and run‑level audit trails.
• Create an evaluation harness for agent or scientist performance (e.g., correctness of exclusions, precedent accuracy, evidence coverage), and integrate lessons from customer projects into continuous improvement.
• Partner closely with ML and bioinformatics teams to expose models and data as agent‑safe tools, and with scientific product to ensure workflows match real discovery practice.
• Contribute directly to near‑term customer deliverables by shipping a minimum viable discovery workflow aligned to long‑term product architecture.

Additional Responsibilities

• Help shape engineering standards for agent reliability, safety, and interpretability in a scientific context.
• Support internal documentation, developer experience, and onboarding as the agent platform becomes a shared foundation across the company.
• Potentially mentor future hires in agent engineering, orchestration, and platform work.

Core competencies

• Strong software engineering background (industry or research), with deep experience building production Python systems.
• Track record designing and deploying workflow/orchestration systems (e.g., DAGs, event‑driven services) in complex domains.
• Experience working in scientific, biotech, or high‑integrity domains where reproducibility and auditability matter.
• Hands‑on experience working close to model APIs while keeping a clean abstraction boundary.
• Excellent systems thinking: ability to balance speed with architecture, and to design modular interfaces that prevent tooling sprawl.
• Experience implementing logging, observability, and evaluation for ML/AI systems.
• Ability to communicate clearly across disciplines.

Nice to have competencies

• Experience with agent frameworks (e.g., LangGraph or similar), retrieval‑augmented generation, or multi‑agent systems.
• Familiarity with ML experiment tracking/model registries (e.g., MLFlow) and data orchestration platforms (e.g. Dagster).
• Exposure to knowledge graph / evidence graph representations or structured scientific reporting.
• Interest in plant biology, gene regulation, or crop improvement (not required, but a plus).

Benefits

• Competitive salary & equity options
• 25 days annual leave & option for 2 weeks work from anywhere policy
• Benefits package
• Career development opportunities as the company scales
• Ownership of ambitious, mission‑driven work with real‑world impact
• Vibrant, innovative & supportive work environment with a committed team
• Access to conferences, events & professional development resources