AI Engineer

Superlivingapp; Hinoba-an; Hybrid; PHP 1,200,000 - 2,400,000; Full time

Benefits offered by this job

Production-scale AI projects

Ownership culture

Flexible work environment

Direct collaboration with founders

Job summary

SuperLiving in the Philippines is seeking an AI Engineer to design and ship AI systems, including personalization engines and conversational AI, powering millions of user interactions.

You will build memory architectures, RAG pipelines, and guardrails, while optimizing latency and cost; work with FastAPI, PostgreSQL, and vector databases in a hybrid setup.

Qualifications

• 2+ years building backend systems or AI-powered applications.
• Experience deploying LLM applications in production.
• Hands-on with RAG, embeddings, and vector databases.
• Experience with async APIs and FastAPI.

Responsibilities

• LLM System Design & Deployment.
• Design and deploy production-grade LLM applications (chat systems, coaching flows, content engines).
• Build robust context management and memory architectures.
• Implement RAG pipelines (chunking, embedding strategies, retrieval tuning).
• Design guardrails and hallucination mitigation systems.
• Develop scalable AI microservices using FastAPI.

Skills

Python

System design

Production LLM deployments

RAG & embeddings

FastAPI

Async APIs

Prompt engineering

Memory systems

Tools

PostgreSQL

MongoDB

Vector databases

LLM evaluation

Embeddings

Job description

About SuperLiving

SuperLiving is India’s first AI-powered lifestyle companion app. We serve users with personalized wellness journeys, expert-led courses, and community-driven experiences. As we scale, AI is not just a feature, it is the core of everything we build.

Role Overview

We are looking for an AI Engineer who has experience building and shipping AI systems in production. You will own the design and development of personalization engines, conversational AI systems, and AI orchestration layers that power millions of real user interactions. This role requires strong system thinking, not just model experimentation.

Key Responsibilities

• LLM System Design & Deployment
• Design and deploy production-grade LLM applications (chat systems, coaching flows, content engines).
• Build robust context management and memory architectures.
• Implement RAG pipelines (chunking, embedding strategies, retrieval tuning).
• Design guardrails and hallucination mitigation systems.
• Optimize for latency, cost, and quality tradeoffs.
• Build personalization engines using behavioral and engagement data.
• Design hybrid ML + rule-based systems for explainability and control.
• Develop scalable AI microservices using FastAPI.
• Design async pipelines, queues, caching layers.
• Work with PostgreSQL, MongoDB, vector databases.
• Evaluation & Reliability
• Build automated evaluation pipelines (LLM evals, AI-as-judge, regression testing).
• Design monitoring and observability for AI behavior in production.
• Debug prompt drift, quality degradation, and cost spikes.

Required Skills & Qualifications

Core

• Strong Python and system design fundamentals.
• 2+ years building backend systems or AI-powered applications.
• Experience deploying LLM applications in production.
• Hands-on with RAG, embeddings, and vector databases.
• Experience with async APIs and FastAPI.
• Understanding of prompt versioning and LLM evaluation.
• Experience building memory systems.

Bonus

• Experience with AI orchestration frameworks.
• Familiarity with cost optimization strategies for AI.
• Experience in high-growth startup environments.

What We Offer

• Opportunity to build AI products for real users
• Gain exposure to production and high scaling AI systems
• High ownership and impact-driven culture
• Flexible work environment
• Work directly with founders and senior engineers.