Description

You will build and maintain the multi-agent orchestration platform, managing the infrastructure that routes user intent across specialized agents.

This role is on-site.

Responsibilities

• Design and implement the LLM-driven orchestrator responsible for delegation, memory management, response validation, and capability discovery.
• Develop the agent selection layer using hybrid retrieval (vector RAG over a capability registry) and closed-set LLM selection with JSON-schema-constrained outputs.
• Build the multi-agent SDK and gateway using FastAPI, implementing path-prefix routing, per-agent tool registries, and session-scoped conversational context.
• Manage tool-driven agents (15–30 tools per agent), owning tool contracts, guardrails, and evaluation metrics.
• Construct the Data API layer with parameterized endpoints between agents and databases, ensuring LLMs never access databases directly.

Required Skills

• 5+ years of experience in software engineering, with a focus on backend services and APIs.
• Strong proficiency with Large Language Models (LLMs) and their integration patterns.
• Experience with JSON schema validation and constraint handling.
• Proficiency in building RESTful APIs using FastAPI or similar frameworks.
• Knowledge of vector databases and RAG (Retrieval-Augmented Generation) architectures.
• Understanding of multi-agent systems, orchestration, and microservices.

Preferred Skills

• Experience with agent-to-agent (A2A) contracts and partner-team onboarding workflows.
• Familiarity with auto-embedding pipelines and dynamic tool composition.

Key Skills

Education

Any Gradute