Agentic AI Engineer: Multi-Tool Agent Architect

webook.com; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

webook.com is seeking an experienced engineer to build multi-step, tool-using agents that plan, retrieve, act, and verify. You will design agent architectures, integrate tools/APIs, and deliver robust execution with safety and observability.

Role requires strong Python engineering, async patterns, and hands-on RAG skills with vector stores. Experience with LangChain/CrewAI or similar frameworks is highly valued for production-grade tool calling.

Qualifications

• Experience building multi-step, tool-using agents and agent architectures.
• Proficient in Python with strong async patterns and error handling.
• Familiarity with LangChain/CrewAI or similar tool-calling frameworks.
• Hands-on knowledge of RAG, embeddings, vector stores, and retrieval quality.

Responsibilities

• Architect agent loops (planning, memory, retrieval, tool use, self-verification).
• Implement tools (functions/APIs/DB queries/files) and MCP-style interfaces.
• Combine RAG with agents: chunking, embeddings, retrieval, reranking, grounding.
• Add guardrails: execution sandboxes, permissions, rate limits, PII policies.
• Build evaluation for agents (task success, autonomy depth, recovery rate).
• Optimize for reliability, determinism where needed, and cost.
• Production experience with LangChain/CrewAI (or similar) and function/tool calling.
• Strong Python engineering; async patterns; robust error handling.
• Practical RAG skills: vector DBs, indexing pipelines, and retrieval quality tuning.
• Systems thinking: queues, retries, idempotency, caching, concurrency control.
• Security & safety for agents (prompt injection, tool scoping, least privilege).

Skills

Python

Async programming

Agent-based systems

LLM tool usage

Tool calling

RAG

Vector databases

Embeddings

Tools

LangChain

CrewAI

APIs

Databases

Job description

webook.com is seeking an experienced engineer to build multi-step, tool-using agents that plan, retrieve, act, and verify. You will design agent architectures, integrate tools/APIs, and deliver robust execution with safety and observability.

Role requires strong Python engineering, async patterns, and hands-on RAG skills with vector stores. Experience with LangChain/CrewAI or similar frameworks is highly valued for production-grade tool calling.