Senior Applied AI Engineer (AI)

TL;DR

Senior Applied AI Engineer (AI): Design and implement LLM-powered product features such as agents, tools, and prompting strategies for scientific and engineering workflows with an accent on production-grade deployment, model evaluation, and integration with backend systems. Focus on building reliable AI workflows, making trade-offs in quality, latency, cost, and establishing engineering standards for applied AI development.

Location: Boston, US / Barcelona, Spain. Hybrid work model, open to remote.

Company

hirify.global builds verifiable, interpretable AI systems combining deep learning with formal logic and physics-based modeling to accelerate semiconductor and photonic hardware development.

What you will do

• Own applied AI features end-to-end: from discovery and design to implementation, rollout, and iteration based on user feedback.
• Build LLM workflows including tool-calling agents, structured output pipelines, retrieval integrations, and safe prompting strategies.
• Select and evaluate LLMs considering quality, cost, latency, reliability; develop prompt patterns, guardrails, and lightweight evaluations.
• Write production-grade code with strong abstractions, testing, instrumentation, reliability, and security practices.
• Collaborate with backend engineers, productionize AI experiments, define workflows, document practices, and mentor junior developers.

Requirements

• 7+ years of software engineering experience (Python preferred) with strong production ownership.
• Experience with LLMs and AI/ML in production: OpenAI API, HuggingFace, LangChain or similar.
• Strong software engineering fundamentals: design patterns, code structure, testing, code review.
• Cloud infrastructure: GCP (Vertex AI preferred) or AWS (SageMaker).
• API development (FastAPI/REST/async), CI/CD (Docker, Terraform, GitHub Actions), monitoring.
• Problem-solving in complex systems, enterprise AI deployment, excellent communication.

Nice to have

• Experience fine-tuning or training models.
• Familiarity with LangChain, Pydantic AI or similar frameworks.
• Prompt engineering, evaluation techniques, real-time inference.
• Background in data engineering, ML engineering, RAG architectures.
• Open-source AI/ML contributions.

Culture & Benefits

• Competitive compensation and stock options.
• Access to cutting-edge tools and collaboration with AI, physics, hardware experts.
• Flexible hybrid/remote work arrangements.
• Professional growth: conferences, research presentations, global AI community engagement.
• Impact-driven culture focused on AI for scientific and engineering challenges.