Agent Infrastructure Engineer — Core Harness (Superagent)

About this job

ImagineArt, a fast-growing generative AI company that has achieved significant ARR and built a top-ranked image generation model without outside funding, is seeking an Agent Infrastructure Engineer for their Core Harness (Superagent) team in India. In this role, you will focus on deep systems and infrastructure rather than basic prompt engineering. You will own Superagent, the core harness driving conversations, tool calls, and multi-step agentic workflows across the company's AI products. A normal day involves designing the execution loop, managing context and memory, handling streaming and retries, building evaluation and observability systems, optimizing for latency and token efficiency, and working closely with product engineering teams to deliver robust AI infrastructure.

Responsibilities

• Own the architecture, development, and evolution of the Superagent core agent harness.
• Design and optimize the agent execution loop for latency, reliability, token efficiency, cost, and task completion.
• Build core harness systems including context management, memory handling, tool routing, and error recovery.
• Build and maintain agent evaluation infrastructure to measure quality and guide data-driven decisions.
• Integrate and benchmark multiple LLM providers and models, evaluating performance, cost, and capabilities.
• Implement performance optimizations such as caching, batching, parallel tool execution, and context compression.
• Build deep observability and instrumentation across agent runs, including tracing, logging, and metrics.
• Work closely with product engineering teams to expose clean abstractions while managing platform complexity.

Requirements

• 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, and unreliable LLM behavior.
• Experience with at least one agent framework such as LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, or a custom harness.
• Experience building or working with evaluation suites, benchmarks, A/B testing, or measurement systems for AI products.
• Strong understanding of concurrency, caching, profiling, and performance optimization.
• Experience working with LLM APIs and production AI infrastructure.

Good to have

• Contributions to open-source agent frameworks, LLM tooling, or AI infrastructure.
• Experience with RAG pipelines, vector databases, or long-term memory systems for AI agents.
• Familiarity with MCP or similar tool-integration standards.
• Experience with LLM inference infrastructure, model routing, rate limits, and fallbacks.
• Experience with Kubernetes, Docker, cloud infrastructure, or distributed systems.

Who should apply

This role suits experienced software or infrastructure engineers with a strong background in backend systems and production-scale LLM agents. Ideal candidates possess deep familiarity with Python or TypeScript, agent orchestration frameworks, performance optimization, and AI observability. Because the posting requires at least 4 years of professional engineering experience, freshers are not eligible to apply.

Frequently asked questions