About the role
Design, develop, and deploy AI agents to automate complex workflows and business processes.
Build agentic AI applications using LLMs and Generative AI technologies.
Develop multi-agent systems that collaborate to solve complex problems.
Integrate AI agents with external APIs, databases, and enterprise applications.
Implement tool calling, function calling, memory management, and task planning.
Develop Retrieval-Augmented Generation (RAG) pipelines for knowledge-based applications.
Work with frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.
Design prompt engineering strategies to improve agent performance and response quality.
Implement guardrails, validation, monitoring, and error-handling mechanisms.
Evaluate AI agent accuracy, reliability, latency, and cost.
Optimize agent workflows for scalability, efficiency, and security.
Collaborate with cross-functional teams to identify automation opportunities.
Document system architecture, workflows, and technical implementation.
Requirements
Strong programming knowledge of Python.
Understanding of Artificial Intelligence, Machine Learning, and Generative AI.
Knowledge of LLMs, prompt engineering, and transformer-based models.
Familiarity with AI agent frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.
Understanding of tool calling, function calling, and agent orchestration.
Knowledge of RAG, embeddings, vector databases, and semantic search.
Experience with REST APIs, JSON, and database integration.
Familiarity with vector databases such as FAISS, Chroma, Pinecone, or Weaviate.
Understanding of Git, debugging, and software development best practices.
Strong analytical, problem-solving, and communication skills.