Software Engineer, Agents
Backend Engineer · Mid · Full Time
Opens Benchling's application page
Role
What you'll do.
Join Benchling's AI Agents team as a Software Engineer to build end-to-end AI agents that accelerate scientific discovery in biotech R&D. You'll design and productionize AI-powered systems automating experiment design, data analysis, and reporting while engineering across the full stack from LLM primitives to React interfaces. This role offers the unique opportunity to shape early-stage AI agent development patterns at a company trusted by over 200,000 scientists and half of the world's top 50 biopharma companies.
Responsibilities
- Build End-to-End AI Agents: Design, prototype, and productionize AI agent systems that automate scientific workflows. This includes building agents that handle experiment design, data capture, analysis automation, and complex scientific report generation. You'll work with large language models and retrieval-augmented generation (RAG) techniques to create agents that can reason about scientific data and make intelligent recommendations to researchers.
- Direct Customer Collaboration: Partner directly with scientific teams at leading biopharma companies and academic institutions to understand pain points, ideate innovative AI agent use cases, and gather continuous feedback. You'll conduct user interviews, build custom evaluations for agent performance, lead product onboarding for new scientific teams, and translate domain-specific scientific workflows into technical requirements.
- Full-Stack Engineering: Develop across the entire technology stack, from backend Python services and LLM integrations to frontend React components. Build robust APIs for agent orchestration, implement authentication and data security mechanisms, design intuitive scientific interfaces, and ensure seamless integration of AI capabilities into Benchling's existing scientific applications.
- Advance Agent Platform Infrastructure: Contribute to frameworks, tooling, and infrastructure that enable faster agent development cycles. This includes building reusable agent patterns, creating debugging and monitoring tools, establishing evaluation frameworks for agent quality, and documenting best practices for agent development that can be leveraged across the organization.
- Shape AI Development Practices: Drive technical experimentation to establish how AI agents should be built and deployed at scale. Influence engineering practices, contribute to product strategy, propose new architectural patterns for agent development, and help evolve development methodologies as the AI agent field rapidly matures and best practices emerge.
Qualifications
What we look for.
Technical
Backend Development
2+ years of professional software engineering experience building and maintaining production systems. Proficiency in Python or similar backend languages with experience building scalable APIs, managing databases, and implementing production-grade software architecture.
Frontend Development
Experience with modern frontend frameworks, particularly React. Ability to build responsive, intuitive user interfaces that make complex scientific workflows accessible. Familiarity with state management, component design patterns, and frontend performance optimization.
AI/LLM Systems
Working knowledge of large language models (LLMs), prompt engineering, and AI agent frameworks. Ability to integrate LLM APIs into production systems, understand token economics, implement cost optimization strategies, and debug AI model behavior in scientific contexts.
Full-Stack Architecture
Capability to architect and implement complete systems spanning backend services, APIs, databases, and frontend interfaces. Experience with system design tradeoffs, scalability considerations, and deployment architectures for production applications.
Education
Computer Science Foundation
Bachelor's degree in Computer Science, Software Engineering, or equivalent professional software engineering experience. A strong foundation in algorithms, data structures, and software design principles is essential for building scalable systems.
Experience
Production Software Development
2+ years shipping production software where you've owned features from conception through deployment, monitoring, and iteration. Experience with the complete software development lifecycle including code review practices, testing strategies, and production support.
Cross-Functional Collaboration
Track record working directly with product managers, designers, and subject matter experts. Experience gathering requirements from non-technical stakeholders, translating business needs into technical specifications, and maintaining communication across distributed teams.
Rapid Iteration and Experimentation
Experience in fast-paced environments where priorities shift and quick pivots are common. Ability to ship minimum viable products (MVPs), validate hypotheses with users, and refine solutions based on real feedback in early-stage product development.
Skills
Required
Python
Production-level Python experience for building backend services, data processing pipelines, and AI agent implementations. Familiarity with async frameworks and common Python libraries for scientific computing.
React
Solid React proficiency including hooks, state management, and component architecture. Ability to build performant, maintainable frontends that integrate with complex backend systems.
LLM Integration
Experience integrating large language models into applications, whether through OpenAI APIs, open-source models, or other LLM platforms. Understanding of prompt engineering, token management, and LLM limitations in production systems.
API Design and Development
Ability to design and implement RESTful APIs (or GraphQL) that are performant, well-documented, and maintainable. Experience with authentication, rate limiting, and API versioning for production services.
Product-Focused Development
Mindset of building features based on user needs and data, not assumptions. Ability to iterate quickly, measure impact, and adjust technical approaches based on user feedback and product metrics.
Preferred
AI Agent Frameworks
Nice to haveFamiliarity with AI agent frameworks and libraries such as LangChain, AutoGPT, or similar tools for orchestrating complex AI workflows and agent reasoning.
Scientific Domain Knowledge
Nice to haveAny background or familiarity with biotechnology, life sciences research, drug discovery, or laboratory information management systems (LIMS). This context accelerates understanding of customer workflows and scientific concepts.
TypeScript
Nice to haveTypeScript experience for type-safe frontend and full-stack development. While not required, TypeScript fluency enhances code quality and developer productivity in complex applications.
Database Technologies
Nice to haveExperience with both relational databases (PostgreSQL) and NoSQL solutions. Understanding of query optimization, indexing strategies, and data modeling for scientific datasets with complex relationships.
Cloud Platforms
Nice to haveDeployment and operational experience with cloud platforms such as AWS, Google Cloud, or Azure. Familiarity with containerization, microservices, and infrastructure-as-code practices for scalable systems.
Testing and Quality Assurance
Nice to haveExperience writing comprehensive unit tests, integration tests, and evaluation frameworks. Knowledge of testing strategies for AI systems including test data generation and validation approaches.
Tech stack
Languages
Frameworks
Databases
Tools
Other
Compensation
Pay and benefits.
Base·USD 259,209 – 350,695
Equity·Stock options
Benefits
Competitive Equity Compensation
Meaningful stock options as part of your compensation package, aligning your success with Benchling's mission to accelerate biotech through AI. You'll have direct ownership stake in the company's growth and success.
Comprehensive Health and Wellness
Comprehensive health insurance including medical, dental, and vision coverage with competitive premiums. Access to mental health resources, wellness programs, and preventive care benefits to support your overall wellbeing.
Professional Development Budget
Annual professional development allowance to invest in learning and growth. Attend conferences, take courses, and pursue certifications in AI, LLMs, biotechnology, or any field that accelerates your expertise and career advancement.
Flexible Hybrid Work
Flexible hybrid work arrangement with required in-office collaboration Monday through Friday at Benchling's San Francisco headquarters. Balance focused work with collaborative brainstorming sessions and direct customer interactions with scientific teams.
Unlimited PTO
Flexible paid time off policy that encourages taking time to recharge, travel, and maintain work-life balance. Trust-based approach to vacation time with no arbitrary limits.
Remote Meeting Flexibility
Support for distributed work on specific projects or circumstances, with clear guidelines and expectations around in-office presence for collaboration and customer engagement.
Learning and AI Integration
Structured support to integrate AI tools and workflows into your daily work. Benchling invests in helping engineers develop AI fluency through training, resources, and collaborative discussions about effective AI usage.
Impact-Driven Culture
Work on technology that directly accelerates scientific breakthroughs and brings life-saving treatments to patients faster. Your work directly contributes to compressing decades of R&D work into years through AI innovation.
Process
Interview steps.
- 01
Initial Screening
Brief conversation with a recruiter to discuss your background, interest in AI agents and biotech, and alignment with Benchling's mission. This is an opportunity to learn about the role and company culture.
- 02
AI Fluency Assessment
As part of Benchling's core interview process, you'll complete a focused AI-related exercise or discussion to demonstrate how you think about AI and use AI tools to drive impact. Feel free to reference any LLM tools, platforms, or AI workflows you currently use, whether ChatGPT, Claude, GitHub Copilot, or other resources.
- 03
Technical Problem-Solving
Technical assessment covering full-stack development capabilities. Expect questions spanning Python backend design, React frontend challenges, API architecture, and potentially LLM integration scenarios. You'll demonstrate your ability to think through complex technical problems and communicate your reasoning.
- 04
System Design Discussion
Conversation about designing an AI agent system for a scientific use case. You'll discuss architecture decisions, scalability considerations, and how to evaluate agent performance. This evaluates your ability to think systematically about building AI products.
- 05
Customer Collaboration Simulation
Scenario-based discussion simulating direct collaboration with scientists or product managers. Demonstrates your ability to translate scientific requirements into technical solutions, gather feedback, and iterate quickly based on user needs.
- 06
Team and Culture Fit
Final conversation with engineering leaders and team members to assess collaborative mindset, curiosity about AI and biotech, and fit with Benchling's fast-paced, experimentation-driven culture. Opportunity to ask questions about team dynamics and company vision.
Full posting
Original listing.
We are rebuilding biotech for the AI era.
When a breakthrough is delayed, the world waits. Getting a molecule from discovery to patients, or a crop from lab to field, involves thousands of slow, manual, disconnected steps. AI has the potential to change this, compressing decades of R&D work into years. But that only happens when clean, structured scientific data and AI are built into how science gets done.
Benchling is the AI platform for biotech R&D. Scientists use Benchling to design experiments, capture structured data, and run AI agents and models directly in their workflows. Over 200,000 scientists around the world trust Benchling to power their most important work, from academic labs to Sanofi, Moderna, and more than half of the world's top 50 biopharma.
We’re building an AI scientist for our customers. We can’t do that if we haven’t built the muscle ourselves. AI fluency is the foundation we build on; it's core to how we work, and we're committed to helping every new hire integrate it into their day-to-day. As part of our interview process, you'll complete a brief AI-focused exercise or discussion so we can understand how you think about and use AI to drive impact in your role. Feel free to reference any tools, platforms, or workflows you use today.
ROLE OVERVIEW
We’re a team focusing on shipping AI agents for scientists, helping them automate toil and accelerate breakthroughs. Our agents automate many parts of scientific work that take hours to weeks today: designing experiments, capturing data, analyzing data, and writing complex reports. As an engineer on the team, you’ll build these agents end-to-end, from designing the agent architecture to shipping intuitive interfaces for the agents within our scientific applications. It’s early days for AI agents, both at Benchling and in the industry at large. We’ll rapidly iterate with customers and change directions quickly, figuring out new patterns for how we develop and go to market. We’ll win if we stay curious and obsess over our customers.
RESPONSIBILITIES
Build end-to-end AI agents, prototyping and productionizing systems that automate scientific work, from experiment design to data analysis and reporting.
Work directly with customers to ideate use cases, gather feedback, build evaluations, and onboard scientific teams.
Engineer across the stack, from developing new LLM-powered primitives to shipping intuitive user interfaces inside Benchling’s applications.
Continuously improve our agent platform, contributing to frameworks, tooling, and infrastructure that accelerate future agent development.
Shape how we build AI at Benchling, driving experimentation, contributing to technical direction, and helping evolve our engineering and product development practices as the field matures.
QUALIFICATIONS
2+ years of professional software engineering experience, building and maintaining production systems.
Experience across the stack, comfort working with backend systems (Python or similar languages) and modern frontend frameworks (React or equivalent).
Strong product sense, with the ability to iterate quickly and refine solutions based on user feedback and data.
Curiosity and excitement about LLMs and AI agents, and a desire to shape how they can transform scientific research.
Collaborative mindset, able to work closely with engineers, product managers, and scientists to bring new ideas to life.
Desire to work in a fast-paced environment, where priorities can shift and rapid experimentation is encouraged.
Interest in learning about biotechnology (no prior knowledge required, just a willingness to learn and adapt).
HOW WE WORK
We offer a flexible hybrid work arrangement that prioritizes in-office collaboration. We’re in the office Monday through Friday.
#LI-Hybrid
#BI-Hybrid
#LI-KW1
Benchling welcomes everyone.
We believe diversity enriches our team so we hire people with a wide range of identities, backgrounds, and experiences.
We are an equal opportunity employer. That means we don’t discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. We also consider for employment qualified applicants with arrest and conviction records, consistent with applicable federal, state and local law, including but not limited to the San Francisco Fair Chance Ordinance.
Redirects to Benchling's application page.
Other roles
More at Benchling.
Software Engineer, Registry and Inventory
Senior
Software Engineer, Backend (Release Engineering)
Mid
Software Engineer, Applications (App Foundations) (High Seniority)
Senior
Software Engineer, Customer Engineering
Mid
Software Engineer, Full Stack, Developer Productivity
Mid