Axiomatic_AI - Applied AI Engineer

• LLM & Agent Workflows: Build LLM-powered workflows such as tool-calling agents, structured output pipelines, retrieval/tool integrations, and safe prompting strategies. • LLM & Agent Workflows: • Production Engineering: Write production-grade code with clear abstractions, stable interfaces, and robust error handling. • Production Engineering: • Testing & Reliability: Learn and apply strong testing practices, including unit tests, integration tests, and golden/regression test suites, with guidance from the team. • Testing & Reliability: • Observability & Debugging: Help add instrumentation for debugging and iteration, including logging, tracing, and metrics for AI features. • Observability & Debugging: • Security & Safety: Learn and follow best practices for safe and reliable AI features, including rate limiting, safe input handling, and prompt-injection awareness. • Security & Safety: • Collaboration & Enablement: Work closely with AI Engineers and researchers to productionize experiments, define deployment workflows from notebooks to production, and document best practices. • Collaboration & Enablement: • 1+ years of industry experience in software engineering (Python preferred), or relevant internship experience combined with strong open-source or project contributions. • Hands-on experience building with modern AI/LLM tools such as the OpenAI API, HuggingFace, or similar, and interest in productionizing prototypes. • Strong programming fundamentals, including design patterns, code structure, testing practices, and code review habits. • Familiarity with cloud environments (GCP or AWS) and containerization tools such as Docker. • Basic experience with API/service development (e.g., FastAPI/REST) and working in a collaborative codebase using Git and code reviews. • Exposure to CI/CD and software delivery workflows (e.g., GitHub Actions or similar) is a plus. • Interest in production reliability, including logging/monitoring, safe rollout practices, and responsible handling of failures. • Problem-solving mindset, with the ability to learn quickly and debug issues in real systems. • Exposure to deploying and operating AI/LLM systems in production or enterprise-like environments. • Clear communication skills and a collaborative approach, including the ability to understand user needs and discuss trade-offs with the team. • Familiarity with agent frameworks such as LangChain, PydanticAI, or similar tools. • Knowledge of prompt engineering and basic evaluation techniques for LLM systems. • Understanding of RAG architectures and retrieval-based systems. • Understanding of Knowledge Graph concepts and how they can support AI systems. • Experience with real-time inference patterns, including streaming responses. • Experience with model fine-tuning or training workflows. • Background in ML engineering or data engineering. • Contributions to open-source AI/ML projects.