AI Ops Engineer

Sovos Latinoamérica

Navi Mumbai

On-site

INR 1,200,000 - 1,800,000

Full time

7 days ago

Be an early applicant

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Sovos is seeking an AI Ops Engineer to own the end-to-end LLMOps lifecycle for its Ask Sovi products. You will drive AI quality, safety, evaluation, observability, and continuous improvement to ensure reliable, scalable AI-powered experiences.

You will gate new agents, design evaluation frameworks, and monitor metrics like drift and safety, while collaborating with product and engineering teams across the globe.

Qualifications

1–3 years in AI Engineering, AI Operations, or related fields.
Experience with LLM observability/evaluation platforms (Langfuse, LangSmith).
Strong understanding of LLMOps, QA for AI, and evaluation frameworks.
Experience with hallucination detection, drift monitoring, safety evaluations.
Experience building evaluation datasets and quality benchmarks.
Familiarity with NLP concepts including embeddings and retrieval.

Responsibilities

Gate new AI agents, prompts, and models before production release.
Design and run evaluation frameworks for deterministic testing.
Build and maintain golden datasets and annotation workflows.
Monitor AI quality, hallucinations, drift, latency, and cost.
Convert customer feedback into measurable quality improvements.
Drive AI adoption and quality standards across product portfolios.

Skills

AIOps

LLMOps

Langfuse

LangSmith

NLP basics

Embeddings

Semantic similarity

Stakeholder mgmt

Job description

Job Description

Build your future with Sovos.

Sovos is transforming tax compliance from a business requirement into a force for growth. Trusted by more than 100,000 customers worldwide, including many of the world's leading organizations, we are leveraging AI to build smarter, more impactful customer experiences.

We're looking for an AI Ops Engineer to own the end-to-end LLMOps lifecycle for a portfolio of Ask Sovi products. You'll drive AI quality, safety, evaluation, observability, and continuous improvement, ensuring our AI-powered experiences are reliable, scalable, and production-ready.

What You'll Do

Gate new AI agents, prompts, and models before production release
Design and run evaluation frameworks using deterministic testing and LLM-as-a-Judge methodologies
Build and maintain golden datasets, annotation pipelines, and human-review workflows
Monitor AI quality, hallucinations, drift, latency, cost, and safety metrics
Convert customer feedback and production learnings into measurable quality improvements
Drive AI adoption and quality standards across your assigned product portfolio

What We're Looking For

1-3 years of experience in AI Engineering, AI Operations, AI Quality Engineering, LLMOps, MLOps, Test Automation, or related disciplines
Experience with Langfuse, LangSmith, Phoenix, or similar LLM observability/evaluation platforms
Strong understanding of LLMOps, AI quality engineering, and evaluation frameworks
Experience with hallucination detection, model drift monitoring, prompt regression management, and AI safety evaluations
Hands-on experience building evaluation datasets, quality benchmarks, and feedback loops
Familiarity with NLP concepts such as embeddings, semantic similarity, classification, and retrieval
Strong product mindset and stakeholder management skills

Ideal Backgrounds

Applied AI Engineers from AI-native or AI-first organizations
Product-minded Engineers with strong customer and business awareness
QA/Test Automation Engineers who have transitioned into AI evaluation
AI Quality Analysts with expertise in hallucination detection, drift monitoring, and LLM-as-a-Judge frameworks

Working Hours

UK Shift

Why Join Sovos?