AI Engineer - Bengaluru

Location: Bengaluru, India

**Overview**
Build AI agents and reliable workflows at Live2.ai. An IC4 individual contributor role covering production AI pipelines, evaluation, reproducibility, and ongoing ownership after launch.

**Company Details**
[Live2.ai](http://Live2.ai) is building an AI-native Social Content & Campaign Intelligence OS for global consumer brands. It helps brands monitor, audit, analyse, and act on intelligence across social content, influencer campaigns, user-generated content, and commerce. The company works with Fortune 500 global enterprise brands.

Website: [https://live2.ai/](https://live2.ai/)

**Requirements**

• Around 3 or more years of software engineering experience, including shipping AI or LLM-backed features to production.

• Experience owning those features after launch, including handling failures and production issues.

• Hands-on experience building evaluation harnesses and using the results to make release decisions.

• Strong general software engineering skills, with an understanding that reliable AI products require substantial systems work.

• Ability to reason about and handle failures in components whose outputs can vary for the same input.

Nice to have:

• Experience with multimodal pipelines involving vision, audio, or document understanding.

• Experience building retrieval systems and evaluating retrieval quality.

• Experience handling adversarial input, prompt injection, or abuse resistance.

• Experience with fine-tuning, distillation, and the supporting infrastructure.

• Experience with workflow orchestration at scale.

**Responsibilities**

• Design and build AI agents and the deterministic workflows they run within.

• Work with Backend Engineers on the services supporting these pipelines.

• Build and operate multi-step AI pipelines that are idempotent, retryable, observable, and resumable after failure.

• Define evaluation datasets, metrics, and release gates before shipping.

• Make model behaviour reproducible through versioning, caching, and replay, so historical decisions can be reconstructed.

• Protect pipelines against adversarial input and prompt injection through system design, beyond prompt instructions alone.

• Measure cost and latency per operation, and treat regressions as bugs.

• Work with Site Reliability Engineers to monitor provider latency, failure rates, and cost.

• Keep the model layer swappable so changing providers requires a configuration change rather than a rewrite.

**Job Details**
Bengaluru, in office.

**Interview Process**

• Initial Screening

• AI Systems and Evaluation Discussion

• Hands-on Engineering Round

• Final Discussion

**Important Note**
ClanX is a recruitment partner, helping [Live2.ai](http://Live2.ai) hire an AI Engineer.