Skip to content
mimi

Applied Ai Automation Engineer

Avyan Global

Remote · India Full-time Yesterday

About the role

Role: Applied AI Automation Engineer

Location: Philippines/India (Preferred overlap with SG hours)
Work Mode: Flexible / Remote
Department: Innovation
Reports to: Head of Engineering

Role Summary

We are looking for an Applied AI Automation Engineer who will partner closely with our digital experts to identify repetitive workflows, design human-in-the-loop automation systems, and deploy practical AI‑powered internal tools.

You’ll own the full lifecycle from architecture and orchestration to deployment and monitoring, turning real business processes into reliable, AI‑driven systems. This role is for builders who have shipped production AI systems, not just prototypes.

The ideal candidate combines strong technical execution with product thinking and can work cross‑functionally with non‑technical stakeholders to deliver meaningful automation impact.

Key Responsibilities

  • Understand existing workflows and identify processes suitable for automation
  • Map current‑state vs future‑state workflows and prioritize automation opportunities based on ROI, complexity, and risk
  • Design and deploy LLM‑powered agents with tool use, memory, and multi‑step reasoning
  • Build automated workflows using frameworks like Lang Graph, Crew AI, or Auto Gen
  • Develop RAG pipelines and integrate with vector databases (e.g., Pinecone, Qdrant)
  • Implement human‑in‑the‑loop systems, guardrails, and fallback logic
  • Integrate with external tools via APIs, webhooks, and MCP
  • Monitor systems for performance, cost, and reliability

Required Skills and Experience

  • 3+ years building and deploying LLM/AI systems in production
  • Strong experience with agent frameworks (Lang Graph, Crew AI, Auto Gen, or similar)
  • Proficiency in Python and/or Type Script
  • Experience with RAG, vector databases, and semantic search
  • Solid understanding of prompt engineering and LLM reliability
  • Hands‑on experience with APIs, cloud deployment, and system integration

We Offer

  • Global Collaboration: Work alongside a diverse team of talented professionals from around the world, gaining insights and experiences that transcend borders.
  • Career Growth: Opportunities to advance within a dynamic and innovative agency, where you'll collaborate with professionals from around the world and contribute to shaping the future of global brands.
  • Comprehensive Benefits: Enjoy comprehensive healthcare coverage, leave and other benefits designed to support your well‑being and work‑life balance.
  • A hybrid working policy

Who Are We?

We are a collective united by one core belief: the future is meant to be designed. A digital agency of curious minds driven by optimism and empathy, we thrive on exploring bold ideas that shape a better tomorrow.

We bring experiences to life by harnessing the power of design, data, and technology. From crafting strategies to creating captivating designs, code, and media content, we transform ambition into reality. Our services encompass everything from media, content, and creative to design and technology solutions.

Diversity, Equity & Inclusion

At Avyan, we take pride in creating an inclusive workplace where everyone has an equal opportunity to thrive. We actively seek to recruit, develop, nurture, and retain talented individuals from diverse backgrounds, with varying skills and perspectives.

Application

Not sure you meet all qualifications? Apply, and let us decide.

Want to know more about Avyan? Check out our website: www.avyan.global

Requirements

  • 3+ years building and deploying LLM/AI systems in production
  • Strong experience with agent frameworks (Lang Graph, Crew AI, Auto Gen, or similar)
  • Proficiency in Python and/or Type Script
  • Experience with RAG, vector databases, and semantic search
  • Solid understanding of prompt engineering and LLM reliability
  • Hands-on experience with APIs, cloud deployment, and system integration

Responsibilities

  • Understand existing workflows and identify processes suitable for automation
  • Map current-state vs future-state workflows and prioritize automation opportunities based on ROI, complexity, and risk
  • Design and deploy LLM-powered agents with tool use, memory, and multi-step reasoning
  • Build automated workflows using frameworks like Lang Graph, Crew AI, or Auto Gen
  • Develop RAG pipelines and integrate with vector databases (e.g., Pinecone, Qdrant)
  • Implement human-in-the-loop systems, guardrails, and fallback logic
  • Integrate with external tools via APIs, webhooks, and MCP
  • Monitor systems for performance, cost, and reliability

Benefits

healthcare coverageleave

Skills

APIAuto GenCrew AILang GraphLLMPythonRAGTypeScriptvector databases

Don't send a generic resume

Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.

Get started free