AI Engineer (Team Lead)

What You Will Do
Design and develop AI agents and multi-agent systems for real-world use cases
Build end-to-end AI-native products (idea → architecture → development → testing → deployment → production)
Use Claude Code / Cursor / Windsurf / similar tools to accelerate development
Implement agent orchestration, memory systems, and tool integrations
Develop LLM-powered pipelines (RAG, fine-tuning, evaluation frameworks)
Integrate APIs, databases, and external systems into workflows
Set up AI-native testing frameworks (prompt testing, evaluation pipelines, agent validation)
Deploy and monitor systems with focus on latency, cost, and reliability

✅ Must-Have Skills
Strong hands-on experience with:
Python (mandatory)
Backend systems & API design
LLM ecosystems (OpenAI, Claude, Gemini, open-source models)
Proven experience in:
AI agent frameworks (LangChain, CrewAI, AutoGen, Google ADK, AWA AgentCore, or custom agents)
RAG pipelines, embeddings, vector databases
Prompt engineering & evaluation
Critical Requirement:Ability to build end-to-end using Claude Code or similar AI coding tools
Experience with “vibe coding” workflows (rapid build → iterate → test → deploy)
Proven ability to go from problem statement → working product → deployed system independently
Understanding of:
Multi-agent architectures
Tool/function calling
Memory systems
Deployment experience:
Cloud (AWS / GCP / Azure)
Docker (Kubernetes is a plus)

⭐ Good to Have
Built or contributed to AI-first products/startups
Experience with AI evaluation frameworks (prompt testing, agent scoring, guardrails)
Exposure to frontend frameworks (React)
Open-source contributions in AI/ML

👤 Who You Are
Strong Computer Science background (Tier-1: IITs, IIITs, BITS, or top global universities)
Have shipped AI systems end-to-end
Thrive in fast, ambiguous environments
Strong bias for execution, speed, and ownership
Able to leverage AI tools to multiply output, not just assist coding