AI Engineer
Job Description
This role focuses on engineering production-ready AI systems, including retrieval-augmented generation (RAG) pipelines and intelligent AI agents. The position is based in Phoenix, AZ onsite and involves building end-to-end workflows that retrieve knowledge, reason over information, use external tools, and automate complex tasks.
Role Overview
As an AI Engineer, you will design, build, and deploy RAG systems and AI agents for enterprise use cases. Work includes integrating large language models, implementing ingestion and retrieval workflows, and improving system performance across accuracy, relevance, latency, cost, and reliability.
Responsibilities
- Design and develop RAG pipelines for enterprise documents, structured data, and knowledge bases.
- Build AI agents that can plan, reason, use tools, and complete multi-step tasks.
- Integrate LLMs from providers such as OpenAI, Anthropic, or open-source platforms.
- Develop document ingestion, chunking, embedding, indexing, retrieval, and reranking workflows.
- Work with vector databases including Pinecone, Weaviate, Milvus, Qdrant, or pgvector.
- Implement agent frameworks and orchestration workflows using tools such as LangChain, LangGraph, LlamaIndex, or comparable technologies.
- Connect AI systems to APIs, databases, business applications, and internal tools.
- Improve response accuracy, relevance, latency, cost, and reliability.
- Create evaluation frameworks for retrieval quality, hallucination detection, agent performance, and end-to-end outcomes.
- Implement security, access controls, observability, guardrails, and human-in-the-loop workflows.
- Collaborate with product, engineering, data, and domain experts to identify high-value AI use cases.
- Deploy and maintain AI applications in cloud or containerized environments.
Required Qualifications
- 3+ years of experience in software engineering, machine learning engineering, or a related field.
- Strong Python skills and experience building production APIs or services.
- Hands-on experience building and deploying RAG applications.
- Practical knowledge of embeddings, semantic search, hybrid search, reranking, and vector databases.
- Experience working with LLM APIs, prompt design, structured outputs, and function/tool calling.
- Experience developing AI agents or multi-step LLM workflows.
- Understanding of data preprocessing, document parsing, metadata management, and knowledge representation.
- Experience with REST APIs, databases, Git, testing, and software development best practices.
- Familiarity with AWS, Azure, or Google Cloud.
- Strong problem-solving, communication, and analytical skills.
Technologies
Python, OpenAI, Anthropic, RAG, vector databases, Pinecone, Weaviate, Milvus, Qdrant, pgvector, LangChain, LangGraph, LlamaIndex, embeddings, semantic search, hybrid search, reranking, LLM APIs, function/tool calling, REST APIs, Git, AWS, Azure, Google Cloud
Location, Duration, and Employment Details
- Job ID: J55809
- Location: Phoenix, AZ (onsite)
- Duration: 11 Months + Extension
- Employment Type: W-2, 1099, C2C
- Domain Exposure: Consumer Staples
- Client: To Be Discussed Later
- Salary/Bill Rate: USD 72 - 72 per hourly
- Bill Rate (C2C): $72/hour
Work Authorization
- US Citizen
- Green Card
- OPT-EAD
- CPT
- H-1B
- H4-EAD
- Other