• Advanced Prompt Engineering: Designing complex, dynamic prompt templates with conditional logic and efficiently reusing information and context within prompts to maximize generation quality and reasoning. • Structured Outputs & Schemas: Implementing various response schemes (JSON mode, function calling, Zod/JSON schemas) to ensure AI outputs are predictable and ready for seamless integration into application logic. • Prompt Engineering & Evaluations: Building robust evaluation pipelines and using Langfuse to collect feedback and score the quality of responses in real time. • Tracing & Debugging: Performing deep debugging of complex LLM chains using Langfuse traces to identify bottlenecks and optimize for cost, latency, and context window usage. • AI A/B Testing: Running systematic experiments across different models via OpenRouter (e.g., comparing Claude 3.5 Sonnet vs. GPT-4o) and analyzing results based on quantitative metrics. • Data-Driven Decisions: Making deployment decisions for new prompts or models strictly based on quantitative benchmarks and trace data, rather than intuition. • Output Scoring & Analysis: Developing scoring systems to analyze the “Problem → Solution” chain and identify root causes of hallucinations or logic errors using Langfuse analytics. • Model Performance & Fine-Tuning: Regularly re-evaluating model performance as new architectures emerge and performing fine-tuning when necessary to meet specific domain requirements.

Role Description Als Legal Engineer bist du die Schnittstelle zwischen Recht, Technologie und Business: - Fokus auf Kundenprojekte & Entwicklung - Prozesse und Workflows: Du analysierst juristische und unternehmerische Prozesse der Kund:innen und übersetzt diese in skalierbare, digitale Workflows in iusta. - Entwicklung: Zu deinen Aufgaben gehört der Aufbau von Datenmodellen, Workflows und Formularen innerhalb unserer Plattform sowie die Entwicklung individueller Skripte und Automatisierungen in JavaScript. - Kundenprojekte: Du leitest Kundenprojekte eigenständig, von der Konzeption bis zur Umsetzung, und gibst Sparring für Legal Teams, Operations und Management. - Produktentwicklung: Du arbeitest eng mit dem Product Team zusammen und bringst Kundenfeedback direkt in die Weiterentwicklung ein. - Support: Du bearbeitest Service- und Supportanfragen unserer Kund:innen und hältst so den Tagesbetrieb am Laufen. Qualifications - Ein Studium im Bereich Wirtschaftsrecht, Jura, BWL oder vergleichbar. - Prozessorientiertes und unternehmerisches Denken. - Projektmanagement-Skills. - Kommunikationsstärke und sicheres Auftreten gegenüber Kunden. - Ein ausgeprägtes Interesse an technischen Themen. - Idealerweise erste Kenntnisse im Programmieren (JavaScript, HTML, CSS). - Bereitschaft, sich schnell in das Schreiben von Skripten (JavaScript) einzuarbeiten. - Erfahrung in Prozessmodellierung (z. B. BPMN) und Umgang mit Tools wie Jira, Confluence, Slack etc. - Kenntnisse in Legal Tech, Automatisierung oder Digitalisierung von Prozessen. Requirements - Du verbindest juristisches Verständnis mit technischem Denken. - Du kannst Anforderungen nicht nur aufnehmen, sondern in konkrete, funktionierende Lösungen übersetzen. - Du hast keine Scheu davor, dich in technische Details einzuarbeiten und Verantwortung für die Umsetzung zu übernehmen. Benefits - Viel Gestaltungsspielraum in einem wachsenden Legal Tech. - Direkter Einfluss auf Produkt und Kundenprojekte. - Flache Hierarchien und schnelle Entscheidungen. - Persönliche Entwicklung in Richtung Consulting, Product oder Leadership. - Flexibles Arbeiten (Berlin / Düsseldorf / Remote). - Starkes Team und echte Ownership-Kultur. - Quereinsteiger:innen Willkommen!

• Building and integrating AI-powered applications and services • Integrating APIs for external LLMs such as OpenAI, Anthropic, and Bedrock • Deploying open-source models like Llama in scalable environments • Contributing to our in-house agent service and its integration into our web application • Extending ReAct-Loop workflows with tool calling • Prompt engineering to improve system behavior • Developing functional primitives for real-time web GIS interactions • Designing and running evaluations against ground-truth datasets • Optimizing latency, response quality, and cost tradeoffs across AI systems

Role Description We are looking for an AI Engineer to build and ship LLM-powered healthcare applications. You’ll have ownership over new AI workflows, from prototype to production. Expect to ship fast, talk directly to customers, and build systems that genuinely reduce clinician burnout. This is a deeply technical role that blends ML, product thinking, and engineering. You'll build and own production services that rely on LLMs, speech models, and medical reasoning. - Develop and own end-to-end AI applications, such as clinical trial matching, ambient copilots, billing automation, and more. - Improve our LLM-powered documentation platform, used daily by thousands of clinicians. - Build and optimize inference pipelines and real-time speech recognition systems. - Collaborate closely with PMs, designers, clinical experts, and GTM teams to iterate rapidly and launch high-impact features. Qualifications - 3+ years building production AI systems, ideally in fast-moving environments or as a founder. - Extensive experience with LLM inference (e.g., OpenAI, Anthropic, Llama, etc.). - Strong product sense. - Comfortable working across the stack (frontend, backend, etc.) to get features shipped. - Obsessed with speed, ownership, and getting real user feedback. Requirements This is a remote position, although Bay Area residents are encouraged to work from our SF office. Nice to Haves - Experience with ASR systems (e.g. Whisper). - Experience with EHR integrations (FHIR, HL7) or healthcare-specific ontologies. - Familiarity with SOC-2, HIPAA, or sensitive data pipelines. Benefits - $150,000 to $250,000 annual salary. - Meaningful equity stake in the company. - Flexible PTO. - Work from home stipend. - Medical, Dental, Vision, 401K. Company Description DeepScribe is building AI agents to automate and transform clinical workflows. Our mission goes beyond note-taking - we’re building the operating system for healthcare. From clinical trial matching to billing and ambient documentation, we’re embedding AI directly into the workflows of the most overburdened professionals in the world. We’ve raised over $60 million in total funding from top-tier investors, including Index Ventures and prominent angels such as Alexandr Wang (fmr CEO of Scale AI) and Dylan Field (CEO of Figma). Our solutions are trusted by some of the largest healthcare organizations in the country, including The US Oncology Network (the nation’s largest oncology network) and Ochsner Health (the largest healthcare system on the Gulf Coast).