Agentic AI Architect

• · AI/ML & Agentic Architecture Design · Architect and deliver Agentic AI systems leveraging LLMs, autonomous agents, tool-using agents, and multi-agent orchestration frameworks. · Architect LLM powered systems · Design end-to-end ML and GenAI architectures including data pipelines, vector databases, RAG patterns, guardrails and AI Governance frameworks, and human-in-the-loop workflows. · Evaluate and integrate modern frameworks such as Langgraph, LangSmith LlamaIndex, Semantic Kernel, AutoGen or enterprise agent platforms. · Define architecture blueprints, solution patterns, reusable components, and best practices. Model Development & Engineering · Build, fine-tune, and optimize ML/Deep Learning/NLP/LLM-based models using Python and mainstream ML frameworks. · Lead experimentation, prototyping, and PoCs for autonomous agents, task decomposition, planning, and self-improving AI workflows. · Implement safety, governance, explainability, drift monitoring, and compliance

controls. MLOps & GenAI Ops · Architect scalable CI/CD pipelines for AI/ML/Agentic solutions. · Deploy AI systems using Docker/Kubernetes, managed ML platforms Collaboration & Leadership · Partner with business teams to translate strategic objectives into AI-driven solutions. · Conduct architectural reviews and guide data scientists, ML engineers, and developers. · Communicate trade-offs, risks, and architectural decisions clearly to stakeholders.

• · ·Overall experience of 10-15 years · 8+ years in AI/ML Architecture · 3+ years of experience in Agentic AI/LLM based systems · Strong experience in Python, TensorFlow · Hands on in ML & LLMs · Cloud experience · Experience in Pharmacy, Healthcare Domain · Experience in designing and deploying AI agents on enterprise-grade runtimes (e.g., Amazon Bedrock AgentCore) including containerized execution, session management, and secure endpoint exposure. · Hands-on experience with agent runtime capabilities including state management, memory handling, asynchronous execution, and integration with external APIs/tools. · Knowledge of observability, monitoring, and debugging of agent executions including tracing, performance tuning, and failure recovery in production environments. · Experience with LLM-as-a-judge, human-in-the-loop evaluation, and rubric-based scoring models for qualitative assessment. Knowledge of hallucination detection, bias/safety evaluation, and grounding validation for enterprise-grade AI systems

• · Generic Leadership Skills § Very good communication skills § Good Analytical skills § Ability to operate within a fast paced work environment a plus § Excellent communication (oral and written), facilitation, presentation, and organization skills required § Excellent organization skills preferred § Proven ability to manage multiple projects simultaneously required § Demonstrated problem solving and organization capabilities preferred

• · Nice to have: · Understanding of pharmacy workflows · Familiarity with healthcare standards: FHIR, HL7, NCPDP, EHR/EMR systems. · Exposure to healthcare compliance: HIPAA, GxP, FDA regulatory frameworks.

Must-Have Skills:

• · Agentic AI
• · Python
• · GenAI
• · MLOps