Generative AI Engineer

Job Title: Lead RAG + LLM Engineer (AI for Social Media Marketing)

Location: Manila, Philippines

Experience: 5–10 years

Role Type: Full-Time, Core Engineering Hire

About

is building the first domain-optimized AI engine for small-business social media marketing. Our platform will learn a business's unique brand voice, products, and customer personas, then automatically create and publish high-performing content using custom LLMs + RAG + predictive scheduling engines.

We are not building generic AI. We are building:

marketing-trained LLMs

brand-voice RAG pipelines

predictive posting models

U.S.-trained datasets and secure inference stack

You will be the technical owner of our AI + RAG architecture.

Key Responsibilities

• Architect and build proprietary Retrieval-Augmented Generation (RAG) pipelines to learn customer brand voices, product catalogs, personas, industry terminology, and competitor context.
• Build embeddings-driven knowledge bases from public metadata (platforms, industries) and user-provided data (business info, brand rules, products).
• Implement vector database strategies (e.g., Pinecone, Qdrant, Weaviate, Chroma) with scalable ingestion and retrieval.
• Develop low-latency inference APIs for real-time post generation, captions, hashtags, social hooks, and creative calls-to-action.
• Build brand-safety constraints, toxicity filters, and identity-preserving personalization on top of LLM outputs.

• Work with product and data teams to develop a Predictive Social Optimization Engine that analyzes historical engagement patterns to choose:

• The best posting times

• The most effective content types

• Audience-specific hooks and caption structures

• Optimize training + inference for low-cost performance at scale, including model distillation, quantization, and caching techniques.

• Build pipelines for reinforcement learning signals based on user engagement and social media analytics.
• Deploy all components securely on U.S.-based infrastructure (Azure), in compliance with SOC-2 style controls and IP protection guidelines.

Core Technical Skills

• AI + RAG + LLM Development
• LLM fine-tuning, embeddings, vector similarity search
• Experience with frameworks such as PyTorch, TensorFlow, LangChain, LlamaIndex
• Experience integrating or training proprietary models (not just calling OpenAI APIs)
• Model compression (quantization, distillation) for low-cost inference
• Retrieval stacks using vector DBs (Pinecone/Qdrant/Weaviate/Chroma)
• Backend + System Engineering
• Strong Python backend architecture
• Django or FastAPI for secure inference microservices
• REST API development at scale
• Microservices, distributed systems, caching
• Cloud + DevOps
• Azure (preferred) or AWS/GCP
• Docker + Kubernetes
• CI/CD best practices
• Secure data handling and private hosting of training assets

Bonus/Highly Valuable Experience

• Building domain-specific knowledge graphs
• Natural language generation focused on marketing or creative writing
• Feature engineering using engagement datasets
• Experience with copyright-compliant dataset curation
• Exposure to sentiment analysis, brand safety classification, and content style transfer

Qualifications

• Bachelor's or Master's degree in Computer Science, AI/ML, Data Engineering, or related field
• 5+ years of backend or AI engineering experience
• Demonstrated experience building and deploying production RAG systems
• Strong communication and leadership skills
• Ability to thrive in a fast-moving startup environment with incomplete specs (you design the solutions)

Why Join Us

• Work on AI that actually solves a real, global problem: small-business marketing
• Build foundational IP in one of the fastest-growing markets (SMBs + AI tools)
• Full ownership over the AI stack (not a subcontractor role)
• Competitive salary + leadership growth + long-term product influence
• Direct collaboration with Microsoft-employed AI engineers and our CEO