Overview
We are looking for an Agentic AI Engineer to design and develop intelligent, autonomous systems that leverage Large Language Models (LLMs), multi-agent frameworks, and context-driven orchestration. You will be responsible for building systems that reason, plan, and act autonomously using generative AI capabilities.Key Responsibilities
Develop and integrate AI agents capable of performing autonomous reasoning and task execution.
Implement multi-agent architectures that communicate, coordinate, and learn dynamically.
Fine-tune and integrate LLMs (e.g., GPT, Claude, LLaMA, Mistral) for contextual reasoning and problem-solving.
Build retrieval-augmented generation (RAG) pipelines using vector databases (e.g., FAISS, Pinecone, or Chroma).
Work with APIs, plugins, and orchestration frameworks (e.g., LangChain, LlamaIndex, CrewAI, AutoGen).
Develop robust monitoring and evaluation frameworks for agentic behavior and performance.
Collaborate with ML and backend teams to integrate agentic systems into enterprise workflows.
Requirements
Bachelor’s or Master’s degree in Computer Science, AI, or related discipline.
3–5 years of experience in AI/ML development with hands-on exposure to LLMs or autonomous systems.
Strong programming skills in Python with experience in LangChain, LlamaIndex, or similar frameworks.
Knowledge of API integration, prompt engineering, and context optimization.
Experience working with cloud AI platforms (Azure OpenAI, AWS Bedrock, Anthropic, or Hugging Face).
Understanding of knowledge graphs, vector databases, and semantic search principles.
Nice-to-Have
Familiarity with Agentic AI frameworks like AutoGPT, CrewAI, or BabyAGI.
Experience deploying AI agents within enterprise automation, RPA, or decision-support systems.
Background in reinforcement learning or AI safety and control mechanisms.