RAG Engineer

Artmac Soft is a technology consulting and service‑oriented IT company that provides innovative technology solutions and services to customers.

Job Type: W2/C2C
Experience: 8+ Years
Location: Prosper, Texas

Responsibilities

• Strong proficiency in Python and experience developing production‑grade AI/ML applications.
• Hands‑on experience building and optimizing Retrieval‑Augmented Generation (RAG) architectures and pipelines.
• Experience with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, or Elasticsearch/OpenSearch.
• Experience with RAG frameworks such as LangChain or LlamaIndex.
• Experience with RAG evaluation frameworks and observability tools.
• Experience deploying AI applications using Docker, Kubernetes, and cloud platforms.
• Experience working with enterprise‑scale documents and knowledge bases (a plus).
• Experience with document chunking, preprocessing, metadata, and context management.
• Hands‑on experience with vector databases and similarity search.
• Experience with RAG evaluation, benchmarking, and quality measurement.
• Understanding of LLMs, prompt engineering, context windows, and hallucination mitigation.
• Strong knowledge of information retrieval concepts such as BM25, dense retrieval, similarity search, and relevance scoring.
• Experience designing scalable and reliable AI/ML services and APIs.
• Familiarity with embedding and reranking models from leading open‑source or commercial model providers.
• Knowledge of FAISS, ANN search, vector indexing, and retrieval optimization.
• Familiarity with CI/CD, Git, REST APIs, and microservices architecture.
• Strong understanding of embeddings and semantic representations.
• Design and implement scalable RAG pipelines for enterprise AI applications.
• Develop effective document ingestion, preprocessing, chunking, and metadata enrichment strategies.
• Build and optimize embedding pipelines using appropriate embedding models for semantic retrieval.
• Design retrieval strategies for structured and unstructured enterprise data.
• Evaluate and benchmark RAG systems using relevant retrieval and generation quality metrics.
• Develop evaluation frameworks and datasets to measure precision, recall, relevance, groundedness, and answer quality.

Qualifications

• Bachelor’s degree or equivalent combination of education and experience.