Back
Remote mid-level role with 4+ years demand but niche LLM-agent specialization limits pure applicant density.
Highly specialized LLM agent infrastructure skills and agent-framework experience reduce cross-industry transferability.
Explicit 4+ years plus mandatory LLM-agent production experience and specific framework and observability skills raises filtering strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own architecture, development, and evolution of Superagent, the core agent harness enabling multi-step agentic workflows across AI products.
Design and optimize the agent execution loop focusing on latency, reliability, token efficiency, cost, and task completion.
Build and maintain infrastructure for context management, tool routing, evaluation, observability, performance optimization, and integrations with multiple LLM providers and AI tools.
Minimum 4 years of experience in software engineering, backend engineering, or systems infrastructure.
Proficiency in Python and/or TypeScript.
Hands-on experience building or operating LLM-based agents in production environments.
Experience with at least one agent framework (e.g., LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, or custom).
Experienced in agent orchestration, multi-step workflows, and managing complex LLM-driven distributed systems.
Strong background in concurrency, caching, performance optimization, and debugging non-deterministic AI systems.
Comfortable designing and maintaining agent evaluation infrastructure with data-driven engineering approach.