Senior Agent Systems Engineer

AI-Native Developer Platform (Vibe Coding) Location: Noida, India Employment Type: Full-Time Reports To: Co-Founder / CTO

About Us: We are building a next-generation AI-native development platform that enables humans and autonomous agents to collaboratively build, modify, test, and deploy software systems. Unlike traditional AI coding assistants, our platform is stateful, agent-driven, infrastructure-aware, multi-step and versioned, and designed for production-grade workflows. We operate at the intersection of code collaboration systems, containerised execution environments, orchestrated infrastructure, and autonomous agent systems powered by LLMs.

We are looking for a Senior Agent Systems Engineer to design and build the orchestration, execution, and infrastructure layers that power our coding agents.

This is not a prompt-engineering role. This is a production systems engineering role with AI orchestration at its core.

Role Overview: You will architect and implement the core systems that allow AI agents to: - Modify repositories across multiple commits - Execute tests in sandboxed environments - Coordinate multi-step plans - Interact with external tools and APIs - Deploy builds to staging or production - Roll back safely on failure - Maintain persistent state across sessions

You will work closely with the Co-Founder/CTO to define the long-term architecture of agent orchestration and execution.

Core Responsibilities: - Design agent orchestration frameworks (planner → executor → validator patterns) - Build robust execution pipelines for long-running AI tasks - Implement structured tool-calling systems - Design memory and state persistence strategies - Create sandboxed code execution environments - Implement rollback and recovery mechanisms - Establish observability for agent behaviour (logs, metrics, tracing) - Design evaluation and regression testing frameworks for agent quality - Ensure reliability, idempotency, and fault tolerance

Required Qualifications: Distributed Systems & Infrastructure Engineering Strong experience designing and operating production systems involving: - Event-driven architectures - Job queues and async workers - Retry strategies and idempotency - Failure isolation and recovery - Distributed locking or coordination - Observability (metrics, logs, tracing) - Scalable backend services

Agent Architecture & LLM Orchestration Demonstrated experience building: - Tool-calling agents - Structured-output LLM workflows - Multi-step reasoning pipelines - Memory systems (short-term vs persistent state) - Context window management strategies - Prompt versioning and evaluation frameworks - Deterministic wrappers around probabilistic models

Secure Execution & Deployment Infrastructure Experience with: - Sandboxed code execution - Containerisation and resource isolation - CI/CD automation - Safe deployment strategies (rollback, staged deployment) - Secrets management - Resource limits and environment isolation

Merit-Based Qualification: We prioritise demonstrated capability over years of experience. If you can design and build production-grade agent orchestration systems at a high level, we encourage you to apply.

Ideal Candidate Profile: - Systems thinker with strong architectural judgment - Comfortable working at the intersection of AI and distributed systems - High ownership mindset - Bias toward reliability and production quality - Able to reason deeply about failure modes - Interested in shaping how autonomous systems build software

Compensation: Competitive salary and meaningful equity. This is a high-impact, foundational engineering role with long-term leverage.

Shaere your resumes at