We are seeking a Senior ML Engineer to join a strategic initiative in the travel sector, focused on building a production-grade Knowledge Graph platform with integrated Retrieval-Augmented Generation (RAG) capabilities.
This role will drive the development of advanced semantic content discovery and relationship modeling solutions, leveraging cutting-edge cloud and ML technologies.
Responsibilities
- Design and implement LLM-based entity and relationship extraction workflows
- Develop prompt templates and orchestration logic for Graph RAG
- Build evaluation frameworks for precision/recall tracking and gold set validation
- Implement human-in-the-loop review workflows
- Optimize LLM usage for cost and performance
- Collaborate with cross-functional teams to align platform features with business goals
- Integrate vector embeddings and similarity search into platform architecture
- Ensure robust API development using REST or GraphQL
- Oversee ETL pipeline development for data ingestion and transformation
Requirements
- 4+ years of experience in ML/AI engineering
- Hands-on experience with LLM APIs such as OpenAI, Anthropic or AWS Bedrock
- Strong prompt engineering and LLM orchestration skills
- Proficiency in Python ML frameworks
- Skills in embedding models and vector similarity search
- Knowledge of AWS services including Neptune, Bedrock, OpenSearch, S3 or Lambda
- Experience with Infrastructure-as-Code using Terraform or CloudFormation
- Competency in CI/CD automation and Git-based version control
- Familiarity with Agile or Scrum project management methodologies
Nice to have
- Experience building RAG (Retrieval-Augmented Generation) systems
- Knowledge of graph neural networks or knowledge graph embeddings
- Background in NLP or information extraction
- Familiarity with LangChain, LlamaIndex or similar frameworks