Senior Applied AI Engineer

About RegASK

RegASK is a pioneering Agentic AI Regulatory Operating System tailored for companies in life sciences and consumer products. The company leverages vertical AI and a global consortium of over 1,800 regulatory subject matter experts to help organizations anticipate regulatory changes, evaluate their impacts, and coordinate compliance activities across more than 160 markets. RegASK's platform integrates regulatory intelligence, decision-making, and workflow execution into a cohesive system designed for contemporary regulatory teams.

RegASK serves departments such as Regulatory Affairs, Quality & Safety, Labeling, Packaging, R&D, and Legal, equipping them to handle increasing regulatory complexities with enhanced speed, assurance, and control. By uniting agentic AI, human expertise, and enterprise governance, RegASK transforms regulatory operations from reactive processes to strategic business competencies.

Position Summary

We are seeking a Senior Applied AI Engineer to join our AI team. This role focuses on the end-to-end ownership of designing, evaluating, and delivering LLM-powered agentic systems integrated into the RegASK platform. The position operates at the intersection of AI innovation and product delivery, requiring development of agent workflows mainly in Python and TypeScript, and close collaboration with product engineering teams within our Node/React environment.

Key Responsibilities

• Develop and implement agent workflows utilizing LangGraph, LangChain, or similar frameworks, emphasizing orchestration, monitoring, and debugging capabilities.
• Create automated evaluation pipelines to assess factual accuracy, robustness, hallucination detection, and guardrails, ensuring quality gates for deployment.
• Enhance embedding model performance, vector store integrations, and retrieval-augmented generation (RAG) pipelines specifically for regulatory domain content.
• Integrate agent-based services directly into the RegASK platform by working within the Node/React codebase alongside the product engineering team.
• Maintain and optimize prompt pipelines focusing on cost efficiency, latency reduction, and accuracy improvements in live production environments.
• Manage deployment, ongoing monitoring, and iterative improvements of Generative AI services (LLMOps), preferably leveraging Azure tools such as ML Studio, Azure OpenAI, and Azure AI Foundry.
• Collaborate with product managers, regulatory experts, and engineers to convert requirements into effective agentic solutions, while mentoring peers on agent design and evaluation methodologies.

Required Qualifications and Experience

• Proven production experience with LangGraph, LangChain, or equivalent agent frameworks.
• Demonstrated ability to own LLM evaluation and monitoring processes to verify and observe agent behavior in production settings.
• Expertise with embedding models and vector databases, including Pinecone, Weaviate, FAISS, or Mongo Atlas Vector Search, along with retrieval optimization strategies.
• Hands-on experience developing and deploying at least one GenAI product to real users from start to finish.
• Strong programming skills in Python (including FastAPI, Transformers, spaCy) and working proficiency in TypeScript with Node.js and React.
• Familiarity with both SQL and NoSQL data modelling and retrieval techniques.
• Solid practices in LLMOps and MLOps covering continuous integration/deployment, monitoring, scaling, and cost management.
• Excellent communication skills with the ability to clearly present system behaviors and evaluation results to non-technical regulatory and commercial stakeholders.

Desirable Skills

• Experience in fine-tuning or adapting LLMs using methods like LoRA, QLoRA, or Direct Preference Optimization (DPO) complementing retrieval and prompting techniques.
• Knowledge of graph databases or knowledge graphs supporting hybrid retrieval-augmented generation.
• Experience with continuous evaluation and A/B testing frameworks for agents in live production environments.
• Background in compliance, life sciences, or regulatory intelligence sectors.

Benefits and Working Conditions

• Flexible working options including hybrid arrangements.
• Opportunity to hold a significant role at the convergence of AI, SaaS, and compliance/regulatory intelligence.
• Support for continuous learning and professional growth.