Description

Key Responsibilities

Design and develop agentic AI systems using LLMs (e.g., GPT, Azure OpenAI, Claude, etc.)
Build multi-agent workflows with planning, memory, and tool usage capabilities
Integrate APIs, enterprise systems, and knowledge sources into agent workflows
Develop prompt engineering strategies and optimize model performance
Implement RAG (Retrieval Augmented Generation) pipelines
Ensure scalability, performance, and security of AI systems
Collaborate with business teams to translate use cases into AI solutions
Monitor agent behavior and continuously improve accuracy and reliability

Required Skills & Experience

3 to 8 years of experience in software engineering / AI development
Strong programming skills in Python (mandatory)
Experience with LLM frameworks: LangChain, Semantic Kernel, AutoGen, CrewAI, etc.
Knowledge of vector databases (FAISS, Pinecone, Azure AI Search, etc.)
Experience with REST APIs and microservices architecture
Familiarity with Azure AI / AWS AI services
Understanding of prompt engineering, embeddings, and fine-tuning concepts

Good to Have

Experience with multi-agent orchestration
Knowledge of GenAI governance and responsible AI
Frontend exposure (React, chat interfaces)

Key Skills

Education

Bachelor's degree