Applied AI Engineer

About us: Axiomatic AI is building a new class of AI systems designed to reason with the rigor of the scientific method. By combining deep learning with formal logic and physics-based modeling, we create verifiable, interpretable AI systems that collaborate with and support human researchers in high-stakes scientific and engineering workflows.  Our mission, 30×30 , is to deliver a 30× improvement in the speed, accessibility, and cost of semiconductor and photonic hardware development by 2030.  We aim to revolutionize hardware design and simulation in these industries and are building a team of highly motivated professionals to bring these innovations from research into commercial products. Position overview:  As an Applied AI Engineer, you will be the bridge between the R&D team and the product, turning research prototypes into robust, production-ready AI capabilities. You will work hands-on across the stack to integrate LLM- and agent-based systems into real workflows, ensuring they are reliable, reproducible, and maintainable in production environments. This role requires strong engineering skills to implement, test, deploy, and operate AI-driven features in production, working closely with researchers and software engineers to meet real-world constraints such as quality, latency, cost, privacy, and reliability. You will also bring a solid understanding of modern AI models, including LLMs and agentic architectures, to make sound technical choices and anticipate failure modes. Your Mission 1. Applied AI Product Development Own applied AI features through the full delivery cycle: design → implementation → rollout → iteration Translate user feedback and research prototypes into clear requirements and working software Build LLM workflows such as tool-calling agents, structured output pipelines, retrieval/tool integrations, and safe prompting strategies Balance iteration speed with production quality: readability, maintainability, and debuggability 2. Model & Prompt Contribution Work with LLMs (OpenAI, Anthropic, HuggingFace, or similar) and contribute to prompt strategy and evaluation Apply structured prompting patterns, schemas, and constraints under senior guidance Participate in lightweight evaluations to catch regressions (golden datasets, acceptance criteria, failure-mode tests) 3. Production Engineering & Quality Write clean, typed Python with solid API boundaries and consistent error handling Own unit tests, integration tests, and golden/regression tests for your features Implement logging, tracing, and basic metrics for AI features you build Follow reliability and security best practices: rate limiting, safe input handling, prompt-injection awareness 4. Collaboration Work closely with AI Developers and researchers to productionize experiments Follow established deployment workflows: notebook/test repository → PR → staging → production Participate actively in code reviews and apply feedback consistently Key Requirements 3+ years of software engineering experience, Python preferred Familiarity with agent frameworks such as LangChain, PydanticAI, or similar Knowledge of prompt engineering and basic evaluation techniques for LLM systems Hands-on experience building with LLMs or AI/ML tools in production (OpenAI API, HuggingFace, LangChain, or similar — beyond prototypes) Strong programming fundamentals: design patterns, code structure, testing practices, and code review habits API/service development experience (e.g., FastAPI, REST, async Python) and collaboration in shared codebases using Git Basic observability experience: logging and tracing for distributed or AI systems Problem-solving mindset: comfortable debugging real issues in production systems Clear communication skills and a collaborative approach Nice to Have CI/CD experience: Docker and GitHub Actions or similar Understanding of RAG architectures and retrieval-based systems Experience with real-time inference patterns, including streaming responses Background in ML engineering or data engineering Understanding of Knowledge Graph concepts and how they can support AI systems Contributions to open-source AI/ML projects What we offer: Competitive compensation Stock Options Plan: Empowering you to share in our success and growth. Cutting-Edge Tools: Access to state-of-the-art tools and collaborative opportunities with leading experts in artificial intelligence, physics, hardware and electronic design automation. Professional Growth: Opportunities to attend industry conferences, present research findings, and engage with the global AI research community. Impact-Driven Culture: Join a passionate team focused on solving some of the most challenging problems at the intersection of AI and hardware.   Why join us?  At Axiomatic_AI, you will be working on technology that drives innovation in AI for scientific and engineerin