Agent Infrastructure Engineer

About the role

ImagineArt is a fast-growing, self-funded GenAI company building one of the world's strongest AI products, including a top-ranked image generation model. As an Agent Infrastructure Engineer, you will own Superagent, the core agent harness powering conversations, tool calls, and multi-step agentic workflows across ImagineArt's AI products. Day-to-day, you will architect and optimize the agent execution loop, build core harness systems (context, memory, tool routing, structured outputs, retries), develop evaluation and observability infrastructure, integrate and benchmark multiple LLM providers, and implement performance optimizations like caching, batching, and parallel tool execution. You will also debug complex non-deterministic, distributed, model-driven systems and collaborate with product engineering to expose clean abstractions. This is a deep systems and infrastructure role based in India, offered as a remote full-time position.

What you’ll do

• Own the architecture, development, and evolution of Superagent, the core agent harness.
• Design and optimize the agent execution loop for latency, reliability, token efficiency, cost, and task completion.
• Build and improve core harness systems including context management, memory/state handling, tool routing, function schemas, structured outputs, retries, and error recovery.
• Build and maintain agent evaluation infrastructure to measure quality and guide engineering decisions with data.
• Integrate and benchmark multiple LLM providers and models, evaluating performance, cost, reliability, and capabilities.
• Implement performance optimizations such as caching, batching, parallel tool execution, and prompt/context compression.
• Build deep observability and instrumentation across agent runs, including tracing, logging, metrics, and regression detection.
• Extend and customize underlying agent frameworks when existing abstractions are insufficient, and debug complex issues across non-deterministic, distributed, and model-driven systems.

What you’ll bring

• 4+ years of experience in software engineering, backend engineering, or systems infrastructure.
• Strong proficiency in Python and/or TypeScript.
• Hands-on experience building or operating LLM-based agents in production.
• Strong understanding of tool calling, function schemas, context limits, structured outputs, model failures, and unreliable LLM behavior.
• Experience with at least one agent framework such as LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, or a custom/homegrown agent harness.
• Strong understanding of agent orchestration and multi-step workflows.
• Experience building or working with evaluation suites, benchmarks, A/B testing, or other measurement systems for AI products.
• Strong understanding of concurrency, caching, profiling, performance optimization, and latency/cost tradeoffs.

Skills

Benefits

Competitive salary and benefits package.