{"has_next":false,"jobs":[{"id":"8bcdba4b-83bb-4857-b449-38d2e9e7d7e1","company_id":"a0000000-0000-0000-0000-000000000001","title":"Prompt Engineer, Agent Prompts \u0026 Evals","slug":"prompt-engineer-agent-prompts-evals-c177ac28","description":"About Anthropic \n Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.\n About the Role \n We’re looking for prompt and context engineers to join our product engineering team to help build AI-first products, features, and evaluations. Your mission will be to bridge the gap between model capabilities and real product experience, working with product teams to build consistent, safe, and beneficial user experiences across all product surfaces.\n You will be deeply involved in new product feature and model releases at Anthropic, combining engineering expertise with an understanding of frontier AI applications and model quality. You’ll become an expert on Claude’s behavioral quirks and capabilities and apply that knowledge to deliver the best possible user experience across models and domains. You’ll be the first resource for product teams working on Claude’s AI infrastructure: system prompts, tool prompts, skills, and evaluations.\n This role requires someone who can effectively balance caring deeply about making Claude the best it can be while also supporting a wide variety of concurrent projects and efforts across many product teams.\n Key Responsibilities \n \n Prompt Engineering Excellence: Design, test, and optimize system prompts and feature-specific prompts that shape Claude’s behavior across consumer and API products.\n Evaluation Development: Build and maintain comprehensive evaluation suites that ensure model quality and consistency across product launches and updates.\n Cross-functional Collaboration: Partner closely with product teams, research teams, and safeguards to ensure new features meet quality and safety standards.\n Model Launch Support: Play a critical role in model releases, ensuring smooth rollouts and catching regressions before they impact users.\n Infrastructure Contribution: Help build and improve the frameworks and tools that allow teams to develop and test prompts and features with confidence.\n Knowledge Transfer: Mentor product engineers on prompt engineering best practices and help teams build their first evaluations.\n Rapid Iteration: Work in a fast-paced environment where model capabilities advance daily, requiring quick adaptation and creative problem-solving.\n \n What We’re Looking For \n Required Qualifications \n \n 5+ years of software engineering experience with Python or similar languages.\n Demonstrated experience with LLMs and prompt engineering (through work, research, or significant personal projects).\n Strong understanding of evaluation methodologies and metrics for AI systems.\n Excellent written and verbal communication skills – you’ll need to explain complex model behaviors to diverse stakeholders.\n Ability to manage multiple concurrent projects and prioritize effectively.\n Experience with version control, CI/CD, and modern software development practices.\n \n Preferred Qualifications \n \n Experience with Claude or other frontier AI models in production settings.\n Background in machine learning, NLP, or related fields.\n Experience with A/B testing and experimentation frameworks (e.g., Statsig).\n Familiarity with AI safety and alignment considerations.\n Experience building tools and infrastructure for ML/AI workflows.\n Track record of improving AI system performance through systematic evaluation and iteration.\n \n You Might Thrive in This Role If You… \n \n Get excited about the nuances of how language models behave and love finding creative ways to improve their outputs.\n Enjoy being at the intersection of research and product, translating cutting-edge capabilities into user value.\n Are comfortable with ambiguity and can define success metrics for novel AI features.\n Have a strong sense of ownership and drive projects from conception to production.\n Are passionate about building AI systems that are helpful, harmless, and honest.\n Thrive in collaborative environments and enjoy teaching others.\n The annual compensation range for this role is listed below. \n For sales roles, the range provided is the role’s On Target Earnings (\"OTE\") range, meaning that the range includes both the sales commissions/sales bonuses target and annual base salary for the role.\n Annual Salary:\n $320,000 — $405,000 USD \n Logistics \n Minimum education: Bachelor’s degree or an equivalent combination of education, training, and/or experience\n Required field of study:  A field relevant to the role as demonstrated through coursework, training, or professional experience\n Minimum years of experience: Years of experience required will correlate with the internal job level requirements for the position\n Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, s","salary_min":320000,"salary_max":405000,"location":"San Francisco, CA","workplace":"hybrid","job_type":"full-time","experience_level":"senior","tags":["nlp","alignment","llm","evaluation","prompt-engineering"],"apply_url":"https://job-boards.greenhouse.io/anthropic/jobs/5107121008","is_featured":false,"is_sticky":false,"status":"active","published_at":"2026-02-03T19:34:17Z","expires_at":"2026-06-29T14:00:20.210758Z","created_at":"2026-04-13T09:35:59.057295Z","updated_at":"2026-05-30T14:00:20.318239Z","company_name":"Anthropic","company_slug":"anthropic","company_logo_url":"https://www.google.com/s2/favicons?domain=anthropic.com\u0026sz=128","quality_score":90,"url":"https://aidevboard.com/job/8bcdba4b-83bb-4857-b449-38d2e9e7d7e1"},{"id":"7895d205-08e7-43b5-b9e8-f9beb1a58f37","company_id":"a25140f5-772d-4c47-947d-7c655ed80737","title":"Clinical Prompt Engineer","slug":"prompt-engineer-229264f1","description":"Truveta provides unprecedented real-world data and real-time intelligence, powered by a dataset built with and owned by US health systems united in a mission of Saving Lives with Data. Together, we power breakthrough medical discoveries, accelerate regulatory-grade evidence, and improve patient care. Today, Truveta enables research on more than 130 million de-identified patients across the US.    \n Achieving Truveta’s ambitious mission requires an incredible team of talented and inspired people with a special combination of health, software and big data experience who share our  company values .   \n Role Overview \n We are hiring a Prompt Engineer with a strong clinical informatics background to build and optimize AI prompts for healthcare and clinical data applications. This role requires hands-on clinical understanding, experience working with real clinical data, experience writing prompts for AI models, and the ability to align LLM prompts with underlying clinical data models.\n You will work closely with clinicians, data engineers, and AI teams to translate clinical questions and workflows into accurate, safe, and scalable AI interactions.\n Key Responsibilities\n \n Design, test, and optimize prompts for LLM-based clinical use cases such as:\n \n Cohort identification\n Clinical question answering\n Concept extraction\n Clinical code mapping\n \n Translate clinical requirements into structured prompts aligned with clinical data schemas\n Collaborate with data engineers to understand how diagnoses, labs, medications, encounters, and outcomes are modeled\n Evaluate AI outputs for clinical accuracy, relevance, bias, and safety\n Apply healthcare data standards (FHIR, SNOMED CT, LOINC, RxNorm, ICD-10-CM) within prompt logic and validation\n Create prompt evaluation criteria and quality benchmarks\n Document reusable prompt patterns and best practices\n Continuously improve prompts based on model behavior and user feedback.\n \n Required Qualifications\n \n 2–5 years of experience in clinical informatics, healthcare analytics, or health IT\n Clinical background required, such as:\n \n Nursing, pharmacy, medicine, public health, or clinical informatics\n OR hands-on experience working with clinical workflows or EHR data\n \n Strong understanding of clinical data modeling, including representation of:\n \n Diagnoses, procedures, medications\n Laboratory results and vitals\n Encounters and outcomes\n \n Practical experience with healthcare data standards:\n \n FHIR\n SNOMED CT\n LOINC\n RxNorm\n ICD-10-CM\n \n Hands-on experience with LLMs and prompt engineering for applied or production use cases\n Ability to critically evaluate AI outputs for correctness and clinical safety\n Strong analytical, documentation, and communication skills\n \n Preferred\n \n Experience with clinical NLP or unstructured clinical text\n Familiarity with EHR systems or clinical data repositories\n Working knowledge of Python for prompt testing or evaluation\n Working knowledge of SQL for exploring clinical datasets\n Experience combining structured and unstructured healthcare data\n Prior work on healthcare AI, decision support, or analytics platforms","location":"Hyderabad, India","workplace":"onsite","job_type":"full-time","experience_level":"junior","tags":["llm","nlp","healthcare","prompt-engineering"],"apply_url":"https://job-boards.greenhouse.io/truveta/jobs/5991211004","is_featured":false,"is_sticky":false,"status":"active","published_at":"2026-05-08T05:52:47Z","expires_at":"2026-06-29T14:14:39.481131Z","created_at":"2026-05-08T14:15:48.629431Z","updated_at":"2026-05-30T14:14:39.593479Z","company_name":"Truveta","company_slug":"truveta","company_logo_url":"https://www.google.com/s2/favicons?domain=truveta.com\u0026sz=128","quality_score":60,"url":"https://aidevboard.com/job/7895d205-08e7-43b5-b9e8-f9beb1a58f37"}],"page":1,"per_page":20,"total":2,"total_pages":1}