Job Title : Agentic AI Engineer
Location : Hyderabad (Onsite)
Role Overview :
Join our advanced AI engineering team and play a key role in building intelligent, autonomous agents that power mission-critical workflows. You will design and operationalize enterprise-grade agentic AI systems that combine decision intelligence, retrieval automation, and LLM-driven orchestration in a highly regulated environment.
Key Responsibilities :
- Architect and develop autonomous AI agents using frameworks like LangChain, LangGraph, or similar tools.
- Build multi-agent systems supporting data retrieval, workflow automation, and complex reasoning.
- Design and implement RAG pipelines using vector databases (e.G., Pinecone, FAISS).
- Integrate and optimize LLMs for generative reasoning, memory, compliance, and guardrails.
- Develop scalable Python-based microservices / APIs for inference, chaining, and orchestration.
- Deploy solutions via Docker / Podman and cloud-native platforms.
- Implement telemetry, observability, & governance — safety checks, bias testing, model evaluation.
- Work closely with Data Science, Product, and MLOps teams to ensure scalable solution delivery.
- Ensure alignment with enterprise AI governance, security, and compliance practices.
Required Skills :
Strong Python development experience.Hands-on expertise in Agentic AI frameworks (LangChain, LangGraph, AutoGen, etc.)Solid understanding of LLMs, embeddings, vector DBs, and memory architectures.Experience in RAG, prompt engineering, agent orchestration.Proficiency in containerization and cloud deployment.Familiarity with monitoring, observability, and AI governance.Excellent analytical, communication, and cross-functional collaboration skills.Preferred Skills :
Experience in healthcare or regulated domains (e.G., HIPAA, PHI compliance).Knowledge of AI safety, governance, and bias mitigation practices.Experience with LLM fine-tuning & optimization (quantization, distillation).Exposure to MLOps tools like MLflow, Weights & Biases.