Senior Agentic AI / AI Systems Engineer

UNIS; India; On-site; INR 4,000,000 - 6,500,000; Full time

Job summary

Item.com seeks a senior hands-on engineer to lead the design and operation of reliable agentic and multi-agent AI systems. This role blends deep implementation with technical leadership, systems judgment, and production accountability.

You will deliver resilient AI platforms, create reusable patterns for evaluation, observability, governance, and cost control, and raise the technical bar through architecture reviews, mentoring, and incident learning.

Qualifications

• Must have production software/systems engineering experience and hands-on AI ownership.
• Experience operating distributed AI/ML or agentic systems at meaningful scale.
• Experience with evaluation pipelines, observability/tracing, security controls, deployment automation, and incident management.
• Ability to lead technical decisions without relying solely on a framework or vendor abstraction.
• Strong communication skills for technical and non-technical stakeholders.

Responsibilities

• Deliver resilient AI systems that support mission-critical business work.
• Create reusable patterns for evaluation, reliability, observability, governance, and cost control.
• Raise the technical bar through architecture, code reviews, mentoring, and incident learning.
• Lead design and implementation of agentic services and multi-agent workflows across models, tools, data sources, and human workflows.
• Define platform patterns for tool contracts, state, orchestration, evaluation, tracing, guardrails, and release management.

Skills

Production engineering

Distributed AI systems

Observability & tracing

Incident management

Technical leadership

Job description

Overview

Item.com is seeking a senior hands-on engineer to lead the design and operation of reliable agentic and multi-agent AI systems. This role combines deep implementation ability with technical leadership, systems judgment, and production accountability.

Responsibilities

• Deliver resilient AI systems that support mission-critical business work.


• Create reusable patterns for evaluation, reliability, observability, governance, and cost control.


• Raise the technical bar through architecture, code reviews, mentoring, and incident learning.


• Lead design and implementation of agentic services and multi-agent workflows across models, tools, data sources, and human workflows.


• Define platform patterns for tool contracts, state, orchestration, evaluation, tracing, guardrails, and release management.

Minimum Requirements

• Deep production software/systems engineering experience and demonstrated hands-on AI systems ownership.


• Evidence of operating distributed, AI/ML, or agentic systems at meaningful scale.


• Experience with evaluation pipelines, observability/tracing, security controls, deployment automation, and incident management.


• Ability to lead technical decisions without relying solely on a framework or vendor abstraction.


• Strong communication skills for technical and non-technical stakeholders.

Preferred Requirements

• Own reliability engineering: SLOs, fallback paths, incident response, root-cause analysis, and capacity/cost planning.


• Review designs and code; mentor engineers and establish engineering standards.


• Partner with security, platform, product, and operations leaders on safe deployment and change management.


• Make clear tradeoffs among performance, quality, reliability, cost, vendor dependencies, and delivery speed.