Job Description: Senior AI Engineer (GenAI + Data Platform – AWS)
Location – – 2-3 days / week in the client's Irvine office, 1 day in their downtown LA office, 1 day remote
Mandatory Areas
Must Have Skills
• Skill 1 – Generative AI / LLM (RAG, embeddings, prompt engineering)
• Skill 2 – AWS Cloud (OpenSearch, Neptune, DynamoDB, ElastiCache/Redis)
• Skill 3 – Vector Search & Retrieval Systems (OpenSearch / vector DB)
• Skill 4 – Graph Databases (Amazon Neptune, knowledge graphs)
• Skill 5 – LLM Frameworks (LangChain / LlamaIndex)
• Skill 6 – Agentic AI Frameworks (LangGraph / AutoGen / CrewAI)
• Skill 7 – Databricks & Apache Spark (data pipelines, embedding pipelines)
• Skill 8 – Backend/API Development (Python, scalable APIs, microservices)
Domain Experience (If any) –
• AI/ML Platform Engineering
• Generative AI / LLM Applications
• Data Platform / Big Data Engineering
Must Have Certifications –
• AWS Certification (Preferred):
• AWS Certified Solutions Architect OR
• AWS Certified Machine Learning Specialty OR
• AWS Data Engineer Certification
Role Summary
We are seeking a Senior AI Engineer to design, build, and scale a production-grade Generative AI and Data Platform on AWS. The role focuses on enabling LLM-powered capabilities through vector search, graph-based knowledge systems, and governed data pipelines.
The ideal candidate will own end-to-end delivery across the AI lifecycle, including:
Data ingestion and knowledge curation
Embeddings and retrieval systems
Backend services and APIs
CI/CD pipelines and deployment
This role will closely partner with product and engineering teams to operationalize AI capabilities in externally facing applications and drive evolution toward agentic AI systems.
Key Responsibilities
1. GenAI Enablement & Integration
Build and operationalize LLM-powered applications using:
Retrieval-Augmented Generation (RAG)
Embeddings pipelines
Prompt orchestration and evaluation frameworks
Design and implement vector search systems using Amazon OpenSearch
Develop graph-based knowledge systems using Amazon Neptune for relationships, lineage, and explainability
Integrate supporting infrastructure:
Amazon ElastiCache (Redis) for session state and caching
DynamoDB for scalable, low-latency data access
Implement agentic workflows using frameworks such as:
LangGraph, AutoGen, CrewAI (or equivalent)
Integrate with LLM frameworks like:
LangChain, LlamaIndex (tool calling, retrieval orchestration, context management)
Define standards for:
Tool integration
Context-sharing patterns (MCP-style designs)
Evaluate LLM models and retrieval strategies across:
Latency
Cost
Accuracy
Context limitations