Senior Agentic AI Engineer

About the role

SAIGroup seeks a Senior Agentic AI Engineer to lead the design of clinical‑grade AI agents that interpret 3D medical volumes and support radiology workflows. The role focuses on building LLM‑driven agents capable of reading MRI, CT, and PET scans, generating reports, and coordinating multi‑step clinical reasoning. Candidates will integrate multimodal foundation models with structured medical memory, develop evaluation frameworks for safety and interpretability, and collaborate with clinicians, scientists, and regulatory teams to translate research into production systems. The position offers competitive compensation, access to high‑compute clusters, and a clear path to impact patient outcomes through cutting‑edge AI research.

What you’ll do

• Architect LLM‑driven medical agents for 3D medical volumes
• Integrate clinical agents with 3D foundation model representations
• Develop evaluation frameworks for trustworthiness, interpretability, calibration, and clinical safety
• Collaborate with clinicians and scientists to co‑design tasks, datasets, and validation protocols
• Benchmark models against datasets like MIMIC, CheXpert, MosMed, LiTS, BraTS, and India‑specific corpora
• Publish findings at top‑tier venues
• Work with regulatory and product teams to translate research into medically viable systems

What you’ll bring

• Experience building LLM-based agents and chain‑of‑thought systems
• Strong background in multimodal learning, vision‑language transformers, contrastive models, or clinical NLP
• Familiarity with medical imaging, radiology workflows, DICOM pipelines, or 3D data representations
• Expertise in PyTorch/JAX and large‑scale training and inference
• Ability to design safe, interpretable, and auditable reasoning systems
• Strong publication record in multimodal, medical AI, agentic systems, or LLMs
• Comfort collaborating with clinicians and biomedical researchers

Nice to have

• Experience with agent frameworks (LangChain, LLaMA Index, Haystack, custom pipelines)
• Background in clinical ontologies, SNOMED, RadLex, or UMLS
• Contributions to medical AI challenges (BraTS, RSNA, MedVQA, MedIC)
• Prior work in multilingual or code‑mixed medical text
• Proven ability to take research concepts into production‑grade systems

Skills

Benefits

• Competitive compensation
• Access to high‑compute clusters + large proprietary datasets
• Full freedom to publish and define development direction
• Cross‑functional collaboration with clinicians, regulatory experts, and product teams
• A clear path to building systems that meaningfully improve healthcare outcomes