AI Engineer

Job Title: AI Engineer

Function: Product & Engineering

Location: Hybrid

Employment Type: Full-Time

Experience Level: [Mid-Level / Senior]

We are looking for an AI Engineer to join our core product team. You will design, build, and continuously improve the AI systems that power ReveonAI's product suite.

This is not a generic AI role. You will be building systems that operate inside GMP-regulated workflows, where the output must be traceable, auditable, and trusted by senior quality professionals. The bar for reliability is high and so is the impact when the work is done well.

What You Will Work On:

AI Pipeline Development

• Design and build Retrieval-Augmented Generation (RAG) pipelines that surface accurate, grounded information from large volumes of GMP documentation. SOPs, batch records, deviation reports, investigation files, and regulatory guidance.
• Develop and maintain prompt engineering frameworks that produce structured, consistent, and review-ready outputs across different product modules.
• Build and improve agentic workflows that support multi-step quality processes (scope definition → root cause analysis → CAPA drafting → report generation).

Output Quality & Auditability

• Implement structured output layers that ensure every AI-generated response is traceable, citation-grounded, and formatted for human review, not raw model output.
• Develop evaluation frameworks to systematically measure and improve model performance on domain-specific tasks (regulatory language, deviation narratives, CAPA structures).
• Reduce hallucination risk through grounding strategies, source attribution, and confidence signaling, critical in a regulated environment.

Platform & Integration

• Build and maintain integrations within secure enterprise environments
• Contribute to API development and backend services supporting the ReveonAI platform.
• Participate in performance monitoring, logging, and continuous optimization of deployed AI systems.

What You Bring:

Required

• 3+ years of hands-on experience building and deploying LLM-based applications in production environments.
• Strong proficiency in Python.
• Practical experience with RAG architectures and frameworks such as LangChain, LlamaIndex, or equivalent.
• Demonstrated ability to design and evaluate prompt engineering strategies for complex, structured outputs.
• Experience working with vector databases (e.g., Pinecone, Weaviate, Chroma, Azure AI Search) and document ingestion pipelines.
• Solid understanding of LLM evaluation, hallucination mitigation, output grounding, retrieval quality measurement.
• Ability to work closely with non-technical domain experts and translate their requirements into reliable AI behavior.

Strongly Preferred

• Familiarity with regulated industries. pharma, life sciences, healthcare, financial services, or legal — where output accuracy and auditability are non-negotiable.
• Experience building agentic workflows or multi-step AI pipelines.
• Knowledge of data privacy, role-based access control, and enterprise security requirements in AI deployments.

What We Offer

• A focused, high-impact role in a company building AI for one of the most meaningful and accountability-driven industries in the world.
• Direct collaboration with a founding team that has deep pharma quality and manufacturing expertise, you will understand the why behind every product decision.
• Work that is grounded in real-world deployment and real user feedback, not just benchmarks.