About the job
About Us:
Axiomatic AI is at the forefront of creating a revolutionary class of AI systems that embody the principles of the scientific method. By merging deep learning with formal logic and physics-based modeling, we are developing verifiable and interpretable AI systems that enhance and support human researchers within critical scientific and engineering processes.
Our ambitious mission, known as 30×30, aims to achieve a 30-fold improvement in the speed, accessibility, and cost of semiconductor and photonic hardware development by the year 2030.
We are committed to transforming hardware design and simulation across these industries and are assembling a team of exceptionally driven professionals to transition innovations from research into viable commercial products.
Position Overview:
As a Senior Applied AI Engineer, you will serve as a vital link between AI research and the production of software. Your responsibilities will include:
- Collaborating with users and internal stakeholders to pinpoint workflows where AI can add significant value.
- Designing and implementing product features powered by large language models (LLMs), utilizing frameworks such as PydanticAI or similar tools.
- Making informed trade-offs among models and methodologies, considering factors such as quality, latency, cost, privacy, and reliability.
- Facilitating AI developers in deploying their work in a reproducible and secure manner.
- Setting engineering standards for applied AI development, including testing, code reviews, maintainability, and operational readiness.
- Working closely with backend engineers to seamlessly integrate AI functionalities into our products.
- Mentoring junior AI developers and overseeing pull requests to guarantee high-quality output and consistent development patterns.
Your Mission:
- Applied AI Product Development
- Oversee applied AI features from start to finish: discovery, design, implementation, rollout, and iteration.
- Convert user feedback into clear technical requirements and realistic delivery plans.
- Create LLM workflows, including tool-calling agents, structured output pipelines, retrieval/tool integrations, and effective prompting strategies.
- Iterate rapidly while maintaining high production quality (readability, maintainability, debuggability).
- Model & Prompt Strategy
- Select and assess LLMs (OpenAI/Anthropic/others) based on tangible constraints: quality, cost, latency, context limitations, and reliability.
- Develop prompt patterns and guardrails, including structured prompts, schemas, constraints, and fallback mechanisms.
- Design and execute lightweight evaluations to prevent regressions.

