About the Role We are developing a next-generation multimodal foundation model capable of understanding medical imaging , clinical documents , and operational context .

We are now building agentic systems that can execute, coordinate, and optimize clinical workflows across radiology, oncology, and cardiology.

As a Senior Research Scientist, you will design and implement workflow-centric AI agents , including multi-agent orchestration , task routing , and clinical workflow automation .

Your work will directly shape how AI collaborates with clinicians and hospital operations teams.

What You Will Work On

- Development of Agentic Clinical Workflows (Core Focus)
- Architect AI agents that can execute multi-step clinical workflows end to end, such as:
- Imaging ordering → prioritization → acquisition → reporting → follow-up
- Oncology staging → treatment planning → monitoring → documentation
- Cardiology testing → diagnosis → risk stratification → longitudinal care
- Encode clinical logic, workflow dependencies, safety steps, and escalation patterns into agent behaviors.
- Build agent pipelines that coordinate across radiology, oncology, cardiology, ED, OPD, and inpatient teams.
- Orchestration of Multi-Agent Systems
- Design orchestration frameworks that break down complex clinical tasks intoatomic sub-tasks and route them to specialized agents (e.g., imaging analysis agent, summarization agent, scheduling agent, retrieval agent).
- Build controllers that enable agents to share context, verify each other’s outputs, and collaborate dynamically.
- Implement workflow-aware state machines or controllers to manage long-running, multi-step clinical processes.




- Integration With Imaging, Clinical, and Operational Systems
- Develop agents that interact with:

- Imaging systems (PACS/RIS)

- Clinical records (EHR/HIS)
- Operational systems (scheduling, triage, queue management)
- Ensure orchestration layers understand real-world constraints like department availability, urgency, and imaging backlogs.
- Build agents capable of responding to workflow events (urgent findings, incomplete scans, patient no-shows, etc.).
- Leveraging the Multimodal Foundation Model
- Use the foundation model’s imaging-text representations to build agents that can:

- Understand 3D studies (CT/MRI/PET)
- Read clinical notes and operational metadata
- Perform reasoning across multimodal patient context
- Apply prompting, tool use, retrieval augmentation, and memory mechanisms to power agent workflows.
- Evaluation, Safety & Reliability
- Define evaluation methods for agentic workflows, including:

- Workflow completion accuracy

- Task routing correctness

- Operational efficiency improvements

- Clinical coherence and safety
- Collaborate with clinicians to identify edge cases and ensure agents support safe clinical practice.
- Build monitoring and guardrail mechanisms for workflow-level safety.

Why This Role Is High-Impact





- You are designing theworkflow brain of next-generation clinical AI systems.
- Your work shapes AI’s role in radiology, oncology, and cardiology operational environments.
- You define new architectures for orchestrated AI that improve clinical efficiency and patient care.
- You help build the world’s firstagentic clinical coordination layer on top of a multimodal foundation model.

What We’re Looking For

- Strong experience in LLM agents, workflow automation, or multi-agent systems.
- Background in multimodal or clinical AI is a plus.
- Familiarity with hospital workflows—especially in imaging-heavy specialties—is strongly preferred.
- Ability to design and implement agent orchestration frameworks.
- Hands-on experience with PyTorch/JAX, transformers, retrieval systems, or agent frameworks (AutoGen, CrewAI, LangChain, etc.).
- Ability to collaborate with clinicians and product teams to translate real-world workflow needs into agentic systems.

Nice to Have

- Experience with PACS/RIS/EHR integration, clinical informatics, or operational workflow tools.
- Knowledge of oncology and cardiology care pathways.
- Prior work with workflow engines, BPMN systems, or orchestration controllers.
- Experience running simulations, RL-based workflow optimizers, or task planners.

What We Offer

- Competitive compensation commensurate with productivity and innovation.
- Opportunity to define the orchestration layer for a recent generation of clinical AI.
- High-compute resources.
- Close collaboration with clinicians, operations leaders, and AI researchers.
- Freedom to publish and innovate in an emerging field.

📌 Senior Developer — Agentic Clinical Workflow & Orchestration (Bengaluru)
🏢 SAIGroup
📍 Bengaluru