DeepJudge provides an AI-powered enterprise search platform that enables law firms to securely retrieve and reuse institutional legal knowledge at scale.
About us: Founded by former Google search engineers with PhDs in AI from ETH Zurich, DeepJudge helps legal teams unlock and apply the knowledge inside their organizations through world-class enterprise search and AI infrastructure – enabling them to automate workflows, build knowledge-powered applications, and turn institutional knowledge into a lasting advantage. Every organization can license the same AI models, but no two organizations share the same institutional knowledge. Decades of experience, work product, and precedent are often fragmented across systems, underused, and inaccessible. DeepJudge makes this expertise instantly available and actionable – helping legal teams find the right information faster, surface relevant knowledge, and apply it where it matters most. Our platform is trusted by many of the world’s leading law firms and legal teams, including Holland & Knight, Gunderson Dettmer, Cozen O’Connor, ArentFox Schiff, CMS Switzerland, Schoenherr, and others. Headquartered in Switzerland with a growing team across North America and Europe, DeepJudge is shaping the future of how professional knowledge is discovered and applied. At DeepJudge, we move with urgency, think rigorously, and work closely with our clients to build products that solve meaningful problems. If you want to help define how AI transforms professional knowledge work, we’d love to hear from you. About the role: Agentic harness is the backbone of our product - it transforms powerful models into reliable enterprise-grade applications our customers can trust. You’ll join a stellar engineering team and will be responsible for the quality of our agents across applied use cases: developing the harness, crafting system prompts to optimize performance of frontier models, and building evaluation systems that keep a continuous pulse on the reliability and robustness of our features. This is a mission-critical role where your decisions compound directly into what our customers experience every day. If you believe that evals are a first-class engineering discipline - not an afterthought - and you want to own the stack that makes AI actually work in the real world, this is your seat. Your responsibilities will include: - Owning the agentic harness powering critical features across DeepJudge - Building and running the evals end-to-end, from design to instrumentation to continuous monitoring - Improving agent quality through both code (harness) changes and prompting - Influencing our model and launch decisions from the agent quality standpoint - Working closely with Legal Engineering, Product, and Customer Success to shape and prioritize harness improvements - Stay current on LLM, GenAI, and agentic AI trends and incorporate those insights into best practices You're a great fit if you: - Have a Master’s degree in Computer Science or a related field, or equivalent practical experience - Are proficient in one or more backend programming languages such as Python, Rust, Go, or C++ - Know how to evaluate agentic systems and design meaningful eval frameworks - Have a strong interest in the latest trends in GenAI and frontier models - Like to build things from scratch without hand-holding - Have built a large application based on LLMs before - (Nice to have) Experience with agentic SDKs - (Nice to have) Familiarity with the evaluation of LLM-based systems What you can look forward to: - Ownership and ability to impact the company, product, and culture from day 1 - Front seat in one of the hottest verticals in AI - Location: Office 5min walking distance from Zurich central station, where we primarily work on site - Collaborative and supportive work environment - Potential for professional growth and advancement within the company At DeepJudge, we believe great teams are built on diverse perspectives and experiences. We are proud to be an equal opportunity employer and are committed to fostering an inclusive, high-performance culture where everyone can thrive. We welcome applicants of all backgrounds and do not discriminate based on race, religion, color, national origin, gender, gender identity or expression, sexual orientation, age, marital status, disability, veteran status, or any other characteristic protected by law. If this role excites you, but you feel you don’t meet every qualification, we encourage you to apply anyway and tell us why you’d be a great fit.