AI Architect - LLM Models

Description :

Responsibilities :

- Lead architecture, design, and implementation of LLM-based and agentic AI systems for clinical and operational use cases.

- Oversee the development of multi-agent orchestration frameworks (reasoning, planning, and task execution) using tools such as LangGraph, CrewAI, or Semantic Kernel.

- Build scalable RAG pipelines and retrieval systems using vector databases (Pinecone, FAISS, Weaviate, Vertex AI Matching Engine).

- Guide engineers on prompt design, model evaluation, multi-step orchestration, and hallucination control.

- Collaborate with product managers, data engineers, and designers to align AI architecture with business goals.

- Manage end-to-end AI lifecycle data ingestion, fine-tuning, evaluation, deployment, and monitoring on Vertex AI / AWS Bedrock / Azure OpenAI.

- Lead scrum ceremonies, sprint planning, and backlog prioritisation for the AI team.

- Work directly with external stakeholders and customer teams to understand requirements, gather feedback, and translate insights into scalable AI solutions.

- Ensure compliance with HIPAA, PHI safety, and responsible AI governance practices.

- Contribute to hiring, mentoring, and upskilling the AI engineering team.

Requirements :

- Deep expertise in LLMs, RAG, and Agentic AI architectures, including multi-agent planning and task

orchestration.

- Hands-on experience with LangChain, LangGraph, CrewAI, or Semantic Kernel.

- Strong proficiency in Python, cloud-native systems, and microservice-based deployments.

- Proven track record of leading AI projects from concept to production, including performance optimisation and monitoring.

- Experience working with healthcare data models (FHIR, HL7 clinical notes) or similar regulated domains.

- Experience leading agile/scrum teams, with strong sprint planning and delivery discipline.

- Excellent communication and collaboration skills for customer-facing discussions, technical

presentations, and cross-team coordination.

- Deep understanding of prompt engineering, LLM evaluation, and hallucination mitigation.

General Skills :

- Strong leadership, mentorship, and people management abilities.

- Excellent written and verbal communication for both technical and non-technical audiences.

- Ability to balance technical depth with product priorities and delivery timelines.

- Adaptability to fast-changing AI technologies and ability to evaluate new tools pragmatically.

- A bias toward ownership and proactive problem-solving in ambiguous situations.

- Empathy for end-users and a commitment to responsible AI in healthcare.

Good to Have :

- Experience leading AI platform initiatives or building internal AI tooling.

- Exposure to MLOps, continuous evaluation pipelines, and observability tools for LLM systems.

- Knowledge of multi-modal AI (text + structured + image data).

- Prior experience integrating AI into production SaaS platforms or healthcare systems.