AI Engineer

Red Nucleus is hiring a AI Engineer to join our global team. This role will be remote.

Our purpose is advancing knowledge to improve lives. We succeed by being the premier provider of strategic learning and development, scientific advisory services, and medical communications solutions for the life sciences industry. Our global team is composed of nearly 800 full-time employees whose commitment to creativity, quality, and on-time delivery is unrivaled in our space.

At Red Nucleus, we believe in providing a rich working environment that pushes us to innovate in ways that engages our employees to be their best selves.  Our culture is about meaningful work, a true sense of community, and fun.  We love to celebrate our people and we are proud to have been Internationally recognized as a “Great Place to Work".    

Role Overview

You'll play a key role in building, running, and improving our GenAI systems. We already have working systems in production, and you'll deepen what's there while raising the bar on quality and reliability. The work spans the full lifecycle — prototyping new techniques, building what proves out, and occasionally running the pipelines yourself to produce deliverables for our scientific and medical writing teams.

Key Responsibilities

• GenAI Development — Design, build, and deploy LLM-powered solutions, integrating API-driven models (e.g., Gemini, GPT) into production with critical features like batching, caching, retries, and audit logging.
• RAG Systems —Design RAG pipelines using document ingestion, chunking, embeddings, vector databases, hybrid search, grounding, and citation-aware responses.
• AI Agents —Develop agentic workflows that use tools, APIs, structured outputs, multi-step reasoning, task planning, and human-in-the-loop review for evidence workflows.
• Research & Prototyping —Explore and prototype emerging GenAI techniques against real problems, evaluate what's worth taking forward into production.
• Production Readiness —Build solid, dependable systems deployed with APIs, cloud services, containerization (Docker), monitoring, LLM observability and tracing (e.g., LangSmith, Langfuse).
• GenAI Delivery — When needed, you may also run these pipelines yourself to produce outputs for the scientific teams.
• Collaboration & Leadership: Work closely with clinical, HEOR, and medical writing teams to deliver actionable insights, iterate based on subject matter expert feedback, and ensure comprehensive documentation.

Required Experience

• Experience: 3+ years building GenAI software solutions.
• Programming: Strong Python skills and a solid grasp of software engineering best practices (testing, API design, code quality)
• LLM Applications: Hands-on experience with RAG, embeddings, vector databases, prompt design, agents, and LLM evaluation
• Frameworks: Experience with LLM application frameworks such as LangChain.
• Deployment: Experience with APIs, databases, cloud platforms (Azure, AWS, or GCP), secure environments, and production monitoring
• Curiosity: A habit of staying current with fast-moving GenAI research and a willingness to experiment

Nice to have

• Background in integrating and fine-tuning open-source LLMs.
• Experience building quick demos using Streamlit/Gradio.
• Exposure to asynchronous task queues (Celery, RQ, Kafka)

Why You’ll Enjoy Working Here

You’ll work across the full lifecycle — from prototyping to running models and delivering outputs ready for scientific teams. We focus on reliability, clarity, and real impact—working closely with domain experts to ensure our AI systems translate into meaningful results.

Diversity, equity and inclusion are valued at Red Nucleus and we believe we have a shared responsibility to provide equal opportunity and foster an inclusive spirit.  We do not discriminate on the basis of race, color, national origin, religion, caste, sexual orientation, gender, age, marital status, veteran status, or disability status.

To learn more about working at Red Nucleus, please visit Careers | Red Nucleus.

#LI-SS1