Senior Full Stack AI Engineer

The Company We are Alloy Therapeutics— a biotechnology ecosystem company empowering the global scientific community to make better medicines together. Through a community of partners, we democratize access to pre-competitive tools, technologies, services, and company creation capabilities that are foundational for discovering and developing therapeutic biologics. The company facilitates affordable, non-exclusive access to the entire drug discovery community from academic scientists, small and medium biotech, to the largest biopharma. At Alloy, we believe our industry should compete on getting the best drugs to patients as quickly as possible, not exclusive access to the best platforms. As a reflection of our relentless commitment to the scientific community, we reinvest 100% of its revenue in innovation and access to innovation. MAY THE BEST DRUG WIN. Alloy is headquartered in Waltham, MA with additional labs in Basel, CH; Cambridge, UK; and Athens, GA. Successful members thrive in our shared culture of accountability, deliberate trust, and open communication. As a team we aspire to work together to exceed expectations and collectively contribute across the global organization to always maintain our nimble, startup culture. Come thrive at Alloy The Team   The Senior AI Software Engineer will join the Insights team. This team builds internal and external software products that power Alloy’s operations, partner portals, and data platforms. Team members collaborate closely with engineering, product, and scientific teams to deliver modern, scalable, and intuitive applications supporting Alloy’s mission of accelerating drug discovery through technology. The Role   As a Senior AI Software Engineer, you will design, build, and maintain end-to-end web and AI-driven applications that leverage large language models (LLMs) and Alloy’s proprietary data to deliver intelligent, interactive tools for scientists and engineers. You will have ownership over key technical decisions across the AI stack, including architecture design, model selection, and tradeoffs between retrieval-based and model-adoption approaches. Your primary focus will be on developing a conversational AI agent with a ChatGPT/Cursor-style interface that integrates securely with Alloy’s unique data ecosystem. This agent will act as an intelligent assistant helping users explore experimental data, automate workflows, and derive insights from complex scientific information. You will operate across the stack, from LLM integration and vector database design to full-stack web interfaces and production deployment, collaborating with data scientists, bioinformaticians, and software engineers to deliver impactful, real-world tools. This role requires a hands-on builder with strong engineering fundamentals, curiosity about AI systems, and comfort working in an environment that encourages innovation and experimentation. You will report to the Head of the Insights division and have autonomy in owning multiple projects, collaborating with international teams, and delivering production-quality AI products. As the team grows, the role offers scope to expand technical leadership responsibilities and influence the long-term AI platform strategy. How You’ll Drive Impact  Design & Build: Architect, develop, and deploy AI-powered web applications and conversational interfaces connected to Alloy’s proprietary datasets. Innovate: Lead the design and implementation of agentic systems that allow users to interact naturally with complex scientific and operational data. Stay current with advances in LLMs and agentic systems, with time and support to evaluate and prototype new approaches relevant to Alloy’s products. Collaborate: Partner with engineering, product, and scientific teams to identify opportunities where AI can enhance Alloy’s research and operations. Integrate: Build secure and performant APIs that connect LLMs, vector databases, and existing Alloy software systems. Deliver: Ship robust, well-tested, and maintainable code while mentoring others and contributing to team best practices. Principal Responsibilities  Design and implement conversational AI agents using modern LLM APIs. Develop intuitive chat-style user interfaces using React and TypeScript. Build retrieval-augmented generation (RAG) pipelines connecting LLMs to internal data sources and scientific knowledge bases. Evaluate and implement model adoption strategies, including prompt engineering, instruction fine-tuning, and lightweight model customization, to improve agent behavior, reliability, and domain performance where appropriate. Implement evaluation, monitoring, and safeguards to ensure AI systems are reliable, secure, regulatory-compliant, and suitable for use with scientific data. Architect APIs and back-end services in Python (Django) to handle secure data access and orchestration. Design and maintain vector databases and embeddings pipelines for contextual data retrieval. Integrate AI services with Alloy’s scientific data infrastructure and cloud environments (AWS preferred). Implement CI/CD workflows, automated testing, and scalable deployment strategies. Collaborate with UX designers to ensure human–AI interactions are seamless and effective. Troubleshoot, debug, and optimize AI-driven applications in production. Contribute to the team’s long-term technical strategy and mentor junior developers. Qualifications Bachelor’s or Master’s degree in Computer Science, Engineering, Machine Learning, or a related field. Prior experience in biotech or life sciences is not required; curiosity and willingness to learn scientific domains are essential.5+ years of experience as a full-stack or software engineer, including production-level work with AI or ML systems. Proficiency in React, JavaScript/TypeScript, HTML, and CSS. Solid back-end development skills in Python (Django or Flask) and RESTful API design. Experience working with large language models and building conversational or agentic interfaces. Familiarity with vector databases (e.g., Pinecone, Weaviate, FAISS) and retrieval-augmented generation (RAG) techniques. Experience integrating AI systems with cloud infrastructure (AWS preferred). Experience working with relational databases (PostgreSQL, MySQL) and ORM frameworks. Understanding of security, data governance, and API design for proprietary or regulated datasets. Experience with Git, CI/CD tools, and agile development practices. Strong understanding of software architecture, scalability, and performance optimization. Excellent communication skills and a collaborative, research-oriented mindset. Independent, self-driven, and comfortable taking ownership of end-to-end projects. Accommodate occasional travel as needed (10%).  Powered by JazzHR