Role Overview
We are looking for an experienced AI/ML Engineer with expertise in Agentic AI to design, develop, and deploy enterprise-grade AI solutions. The ideal candidate should have strong experience in Python, LLMs, RAG, multi-agent systems, and cloud platforms.
Responsibilities
- Design and deploy enterprise-grade autonomous AI agents.
- Build AI workflows with reasoning, planning, memory, and task orchestration.
- Develop RAG pipelines using vector databases and embedding models.
- Integrate AI agents with enterprise applications and APIs.
- Implement tool calling, guardrails, and feedback mechanisms.
- Deploy AI solutions using Docker, Kubernetes, and cloud services.
- Ensure Responsible AI, security, monitoring, and observability.
Requirements
- Strong Python programming skills.
- Experience with LangGraph, LangChain, CrewAI, or AutoGen.
- Proficiency with OpenAI, Azure OpenAI, or Anthropic.
- Expertise in RAG and Vector Databases.
- Experience with Prompt Engineering and Multi-Agent Systems.
- Knowledge of REST APIs, Docker, Kubernetes, and cloud platforms (Azure, AWS, or GCP).
Nice to Have
- Semantic Kernel
- Knowledge Graphs
- Enterprise Copilot Development
- Reinforcement Learning (RL)
- LoRA Fine-Tuning
- AI Supervisor Architectures
Skills
- Python
- LangChain
- OpenAI
- Vector Databases
- Docker