AI/RAG engineer

CoinMarketCap; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

BNB Chain is seeking an experienced AI systems engineer to advance retrieval-augmented generation and AI search agent development. You will architect end-to-end RAG pipelines, optimize vector search using OpenSearch, and implement grounding and citation to anchor answers to source passages.

You will also automate evaluation and monitor latency and costs in production. Ideal candidates have 3+ years building AI systems with RAG focus, strong Python skills, and hands-on experience with frameworks

Qualifications

• Bachelor's or Master's in CS/AI/ML or related field.
• 3+ years building AI systems with a focus on retrieval-augmented generation (RAG).
• Proven track record in building and optimizing end-to-end RAG pipelines.
• Experience with AI search agent development using frameworks like ReAct, LangGraph, Dify, or CrewAI.
• Hands-on experience with OpenSearch or similar vector search technologies.
• Proficiency in Python and relevant ML frameworks (PyTorch, TensorFlow).

Responsibilities

• Build AI search agents, including planning and multi-agent architectures, via custom or frameworks like LangGraph, Dify, or CrewAI.
• Create end-to-end RAG pipelines from ingestion to hybrid vector search, ideally using OpenSearch.
• Operate and monitor vector/hybrid indexes (OpenSearch) in production.
• Implement grounding and citation linking to source passages.
• Automate evaluation with synthetic QA, retrieval-hit-rate tracking, and model-critique loops.
• Coordinate external tools or knowledge bases, monitoring latency and cost at scale.

Skills

RAG development

Python programming

ML frameworks

AI systems design

Education

Bachelor's or Master's in CS/AI/ML

Tools

OpenSearch

ReAct

LangGraph

Dify

CrewAI

Job description

Job Responsibilities

1. Building AI search agents- including ReAct, planning, and multi-agent architectures via custom implementation or frameworks like LangGraph, Dify, or CrewAI.
2. Building end-to-end RAG pipelines from ingestion, chunking, embeddings, and hybrid vector search, ideally using Opensearch.
3. Operating and monitoring vector/hybrid indexes (e.g. OpenSearch) in production environments.
4. Implement grounding and citation to link generated answers back to their exact source passages.
5. Automate evaluation using synthetic QA, retrieval-hit-rate tracking, and model-critique loops to continuously measure accuracy and detect drift.
6. Orchestrating external tools or knowledge bases and monitoring latency and cost at production scale.

Qualifications

1. Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
2. 3+ years of experience in developing AI systems, with a focus on retrieval-augmented generation (RAG).
3. Proven track record in building and optimizing end-to-end RAG pipelines.
4. Experience with AI search agent development using frameworks like ReAct, LangGraph, Dify, or CrewAI.
5. Hands-on experience with OpenSearch or similar vector search technologies.
6. Proficiency in Python and relevant machine learning frameworks (e.g., PyTorch, TensorFlow).
7. Strong understanding of data ingestion, chunking, embeddings, and hybrid vector search techniques.
8. Experience with monitoring and managing production environments.
9. Knowledge of grounding and citation techniques in AI-generated content.
10. Familiarity with synthetic QA datasets and evaluation metrics.