AI/ML Engineer

Job Title: AI/ML Engineer
Location: Milpitas, CA (Hybrid – 4 days onsite)
Duration: 6+ Months

Job Summary

STAFFXPERT LLC is seeking an AI/ML Engineer on behalf of our client in Milpitas, CA to join a high-impact engineering team focused on building next-generation Generative AI systems.

In this role, you will transform advanced AI architectures into scalable, production-ready systems. You will work closely with senior AI architects to develop the core intelligence layer of an enterprise AI platform, with a strong emphasis on Retrieval-Augmented Generation (RAG) pipelines, multi-agent orchestration, and high-performance data systems.

Key Responsibilities

RAG Pipeline Development

• Design and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines
• Extract and process high-quality data from PDFs, wikis, FAQs, and enterprise knowledge sources
• Develop advanced chunking strategies and metadata enrichment techniques
• Improve retrieval accuracy and relevance through iterative tuning

Vector Database & Search Systems

• Work with vector databases such as Qdrant, Pinecone, or Weaviate
• Design hybrid search systems combining keyword and semantic retrieval
• Implement efficient indexing strategies (e.g., HNSW) and optimize similarity search performance

Multi-Agent Systems

• Build agentic workflows using frameworks such as LangGraph, Agno, or Google ADK
• Develop tools, state management systems, and inter-agent communication logic
• Orchestrate multi-agent pipelines for complex business automation use cases

Data Engineering for AI

• Build scalable ETL pipelines for unstructured and semi-structured data
• Transform raw content into structured, searchable knowledge bases
• Maintain data quality, versioning, and governance standards

Evaluation & Optimization

• Evaluate system performance using frameworks such as RAGAS or LangSmith
• Optimize prompts, retrieval pipelines, and orchestration logic
• Reduce hallucinations and improve response relevance and consistency

Deployment & Scaling

• Containerize applications using Docker
• Deploy low-latency, production-grade AI services
• Ensure scalability, reliability, and performance optimization in production environments

Technical Requirements

• Strong proficiency in Python (including Asyncio, FastAPI, and Pydantic)
• Hands-on experience with agentic AI frameworks (LangGraph, Agno, or Google ADK)
• Experience with vector databases such as Qdrant, Weaviate, Pinecone, or similar
• Strong understanding of similarity search, embeddings, and HNSW indexing
• Experience building RAG systems and working with LLM-based applications
• Strong background in processing and structuring unstructured data sources
• Familiarity with production deployment practices for AI systems