Description :

Job Title : Agentic AI Engineer

Experience : 7+ Years (3+ Years in AI/ML, 1+ Year in Agentic AI)

Location : Hyderabad Onsite

Notice Period : Immediate Joiners Preferred

Interview Mode : Virtual (2 Rounds)

Client : Healthcare Domain (Fortune 100)

Role Overview :

We are seeking a highly skilled Agentic AI Engineer to design, build, and operationalize intelligent agent-based systems for enterprise healthcare applications.

The role focuses on developing autonomous AI workflows using frameworks like LangChain, LangGraph, and other agentic AI tooling. You will work on retrieval-augmented intelligence workflows, multi-agent coordination, AI safety, and enterprise-grade deployments.

Key Responsibilities :

- Architect and develop autonomous AI agents using LangChain, LangGraph, AutoGen, or similar frameworks.

- Build multi-agent workflows for enterprise tasks such as data retrieval, task automation, and reasoning systems.

- Implement RAG pipelines with vector databases (Pinecone, FAISS, Milvus, Chroma).

- Integrate LLMs for generative tasks with prompt chaining, memory systems, guardrails, and fine-tuning.

- Develop Python-based APIs/microservices to support inference, agent orchestration, and event-driven workflows.

- Deploy AI systems using Docker/Podman with cloud-native toolchains (AWS, Azure, GCP).

- Implement observability & monitoring : telemetry, evaluation metrics, safety & bias detection, traceability.

- Work with cross-functional teams (DS, Engineering, MLOps, Compliance) to build scalable and compliant AI solutions.

- Ensure adherence to enterprise AI governance including data security, privacy (PHI), regulatory compliance, and risk controls.

Required Skills :

- Strong proficiency in Python for backend, automation, and AI development.

- Deep hands-on experience with agentic AI frameworks (LangChain, LangGraph, AutoGen, LlamaIndex).

- Experience building and optimizing RAG architectures with vector DBs.

- Strong understanding of LLMs, embeddings, prompt engineering, agent memory, and tool-use.

- Proficiency with containerization (Docker/Podman) and cloud deployment.

- Experience with model evaluation, observability, and AI governance frameworks.

- Excellent problem-solving and communication skills; ability to work in cross-functional setups.

Preferred Skills :

- Experience working in healthcare or regulated industries (HIPAA, PHI).

- Understanding of AI safety, bias testing, explainability, and model audit processes.

- Experience with LLM fine-tuning (LoRA, QLoRA, distillation, quantization).

- Familiarity with MLOps platforms such as MLflow, Weights & Biases, Vertex AI, or Sagemaker.