Job Title : Agentic AI Engineer
Location : Hyderabad - Onsite
Role Overview :
As an AI Systems Engineer, you will be responsible for designing, developing, and deploying intelligent, agent-driven AI systems within the healthcare sector, with a focus on enterprise-grade applications. Utilizing frameworks such as LangChain and LangGraph, you'll build autonomous agents to enhance decision-making, optimize workflows, and orchestrate intelligent services—all while ensuring compliance in a regulated environment.
Key Responsibilities :
- Architect and build autonomous AI agents using LangChain, LangGraph, or other relevant frameworks.
- Develop multi-agent workflows tailored to enterprise use cases, including data retrieval, task automation, and reasoning.
- Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.G., Pinecone, FAISS) and prompt chaining.
- Integrate Large Language Models (LLMs) for generative tasks, applying fine-tuning, safety guardrails, and memory systems as needed.
- Create Python-based microservices and APIs to facilitate agent interactions, inference, and orchestration.
- Deploy AI solutions using containerization technologies (Docker, Podman) and cloud-native infrastructures.
- Implement telemetry, observability, and governance measures, including model evaluation, bias testing, and safety checks.
- Collaborate closely with Data Science, MLOps, and Product teams to ensure the successful delivery of scalable AI solutions.
- Adhere to enterprise AI governance standards, including data privacy, compliance, and security protocols.
Experience & Qualifications :
7+ years of experience (including 3+ years in AI / ML and 1+ year in agentic AI).Strong proficiency in Python development.In-depth experience with agentic AI frameworks such as LangChain, LangGraph, AutoGen, etc.Hands-on experience with vector databases (e.G., Pinecone, FAISS) and RAG architectures .Solid understanding of LLMs , embeddings, prompt engineering, and memory systems.Experience with containerization (Docker, Podman) and cloud deployment .Proficient in telemetry , observability tools , and AI governance (model evaluation, bias testing, safety checks).Strong problem-solving, communication, and cross-functional collaboration skills.Preferred Qualifications :
Prior experience in healthcare or other regulated industries (e.G., HIPAA, PHI).Familiarity with model audits , AI safety , and bias mitigation strategies.Experience in LLM fine-tuning and optimization techniques (e.G., quantization, distillation).Knowledge of MLOps frameworks such as MLFlow and Weights & Biases.