Senior Agentic AI Engineer — Agentic Medical AI at SAIGroup

<p><strong>About the Role</strong></p> <p>We are building a new class of&nbsp;<strong>clinical-grade AI agents</strong>&nbsp;powered by a foundational model that unifies&nbsp;<strong>3D volumetric medical data</strong>&nbsp;and&nbsp;<strong>textual reasoning</strong>. These agents will assist with radiology workflows, treatment planning, case summarization, longitudinal patient analysis, and human-in-the-loop clinical decision support.</p> <p>In this role, you will design the&nbsp;<strong>agent layer</strong>&nbsp;that transforms a powerful multimodal foundation model into a safe, reliable, adaptive medical assistant capable of analyzing 3D scans, retrieving past cases, explaining findings, and coordinating multi-step reasoning chains.</p> <p>This position is ideal for researchers from multimodal/VLM/CLIP ecosystems who want to move up the stack into&nbsp;<strong>autonomous medical reasoning</strong>, multimodal alignment, and real-world clinical impact.</p> <p>&nbsp;</p> <p><strong>What You Will Work On</strong></p> <ul> <li>Architect&nbsp;<strong>LLM-driven medical agents</strong>&nbsp;capable of:</li> <ul> <li>Reading &amp; interpreting&nbsp;<strong>3D medical volumes</strong>&nbsp;(MRI, CT, PET).</li> <li>Answering radiology questions, generating report drafts, and performing differential reasoning.</li> <li>Retrieving similar prior cases using contrastive embeddings.</li> <li>Synthesizing multi-instance evidence across scans, labs, and notes.</li> <li>Executing multi-step “clinical workflows”—image → analysis → summary → recommendation.</li> </ul> <li>Integrate clinical agents with the 3D foundation model’s representations, enabling&nbsp;<strong>structured medical reasoning</strong>and&nbsp;<strong>contextual memory</strong>&nbsp;across longitudinal data.</li> <li>Develop evaluation frameworks for&nbsp;<strong>trustworthiness, interpretability, calibration, and clinical safety</strong>.</li> <li>Collaborate with clinicians and scientists to co-design tasks, datasets, and validation protocols.</li> <li>Benchmark models against open and proprietary datasets: MIMIC, CheXpert, MosMed, LiTS, BraTS, and India-specific clinical corpora.</li> <li>Publish findings at top-tier venues (MICCAI, NeurIPS, AAAI, EMNLP).</li> <li>Work with regulatory and product teams to translate research into medically viable systems.</li> </ul> <p>&nbsp;</p> <p><strong>Why This Role Appeals to CLIP / VLM / Chitrarth / Patram Authors</strong></p> <ul> <li>A rare opportunity to work at the intersection of&nbsp;<strong>agentic LLMs</strong>,&nbsp;<strong>multimodal 3D vision</strong>, and&nbsp;<strong>clinical intelligence</strong>.</li> <li>Ability to bring&nbsp;<strong>contrastive learning</strong>,&nbsp;<strong>cross-lingual modeling</strong>,&nbsp;<strong>multimodal alignment</strong>, and&nbsp;<strong>document understanding</strong>&nbsp;into the medical domain.</li> <li>Greenfield space: medical agent design is still&nbsp;<strong>unexplored</strong>&nbsp;compared to 2D VLMs.</li> <li>Freedom to publish, open source, and propose new clinical reasoning benchmarks.</li> <li>Attractive to researchers who want impact beyond academic settings—directly improving physician workflows and patient outcomes.</li> <li>A chance to create India’s first&nbsp;<strong>medical foundation-model agent system</strong>, setting global standards.</li> </ul> <p>&nbsp;</p> <p><strong>What We’re Looking For</strong></p> <ul> <li>Experience developing&nbsp;<strong>LLM-based agents</strong>, tool-using models, chain-of-thought systems, or orchestrated pipelines.</li> <li>Strong background in&nbsp;<strong>multimodal learning</strong>,&nbsp;<strong>vision–language transformers</strong>,&nbsp;<strong>contrastive models</strong>, or&nbsp;<strong>clinical NLP</strong>.</li> <li>Familiarity with&nbsp;<strong>medical imaging</strong>, radiology workflows, DICOM pipelines, or 3D data representations.</li> <li>Expertise in PyTorch/JAX and large-scale training and inference.</li> <li>Ability to design safe, interpretable, and auditable reasoning systems.</li> <li>Strong publication record in multimodal, medical AI, agentic systems, or LLMs.</li> <li>Comfort collaborating with clinicians and biomedical researchers.</li> </ul> <p>&nbsp;</p> <p><strong>Nice to Have</strong></p> <ul> <li>Experience with agent frameworks (LangChain, LLaMA Index, Haystack, custom pipelines).</li> <li>Background in&nbsp;<strong>clinical ontologies</strong>, SNOMED, RadLex, or UMLS.</li> <li>Contributions to medical AI challenges (BraTS, RSNA, MedVQA, MedIC).</li> <li>Prior work in multilingual or code-mixed medical text.</li> <li>Proven ability to take research concepts into production-grade systems.</li> </ul> <p>&nbsp;</p> <p><strong>What We Offer</strong></p> <ul> <li>Competitive compensation.</li> <li>Access to high-compute clusters + large proprietary datasets.</li> <li>Full freedom to&nbsp;<strong>publish</strong>&nbsp;and define development direction.</li> <li>Cross-functional collaboration with clinicians, regulatory experts, and product teams.</li> <li>A clear path to building systems that meaningfully improve healthcare outcomes.</li> </ul> <p>&nbsp;</p>