Job DescriptionExperience: 10+ Years (including ~2 years relevant agentic AI experience)
nLocation: Pune (In Office)
nExperience: 10+ Years (including ~2 years relevant agentic AI experience)
nSkills required
n
- n
- Agent & sub‐agent architecturen
- Ability to design multi‐agent systems with planners, workers, and specialized sub‐agents, including transparent hand‐off protocols and failure‐handling.n
- Around 2 years of relevant experience building and operating agentic workflows in real projects or products.n

n
- n
- MCP servers and integrationsn
- Hands‐on experience designing and implementing MCP servers that expose internal APIs, databases, and workflows to agents in a secure and observable way.n
- Practical knowledge of MCP client integration, transports (e.g., STDIO/HTTP), authentication/authorization, and managing connections to multiple MCP servers.n

n
- n
- Context management & data accessn
- Strong understanding of context engineering: chunking, summarization, windowing, and context isolation for long‐running or multi‐step agent flows.n




- Ability to choose and justify between MCP‐exposed tools, private data stores, and RAG/vector search for internal data, considering latency, security, and governance.n

n
- n
- Prompting, safety, and guardrailsn
- Experience designing robust prompts for tools and agents, including patterns to mitigate prompt injection, prompt stuffing, and data‐exfiltration risks.n
- Familiarity with permissioned tools, human‐in‐the‐loop reviews, and policy checks before sensitive actions (e.g., code changes, production-impacting calls).n

n
- n
- Autonomous workflows & Ralph loopsn
- Experience setting up Ralph‐style or similar long‐running coding loops that iteratively modify codebases, gated by tests, linters, and explicit stop conditions.n
- Skills in observing, logging, and debugging agent runs (traces, run logs, metrics) and iterating on prompts/skills/MCP design based on real‐world feedback.n
- Cloud technol

📌 AI Agent (Pune)
🏢 WatchGuard Technologies
📍 Pune