AI Engineer at eTeam in Richardson, TX
- Company: eTeam
- Location: Richardson, TX
- Posted: Sep 18, 2026
- Type: Contract
- Experience: 7+ years
Overview
Job Title: AI Engineer Location: Richardson, TX 75082 (Onsite) Duration: 12 Months Experience: 7+ years overall, with 5+ years in AI/ML development RAG & LLM Engineering — Build RAG solutions, agent workflows, prompt grounding and LLM fine-tuning.
Job description
- Job Title: AI Engineer
- Location: Richardson, TX 75082 (Onsite)
- Duration: 12 Months
- Experience: 7+ years overall, with 5+ years in AI/ML development
Responsibilities
- RAG & LLM Engineering — Build RAG solutions, agent workflows, prompt grounding and LLM fine-tuning.
- Enterprise API Integrations — Develop OAuth 2.0/MSAL integrations with Microsoft Graph, SharePoint, Outlook, Planner, OneDrive, ServiceNow and Splunk.
- Vector Search — Design and optimize Qdrant/Milvus-based vector databases, embeddings, retrieval, filtering and reranking.
Requirements
- Python 3.11, advanced type hints, async programming
- LangGraph and LangChain
- Azure OpenAI / OpenAI APIs
- FastAPI, REST APIs
- Vector Databases — Qdrant and/or Milvus
- RAG, prompt engineering, grounding, agent development
- PostgreSQL 16/17, SQLAlchemy, Alembic, advanced SQL
- Docker and Linux
- Redis, Pydantic, Pandas, PyArrow
- ETL/ELT and Prefect 2.x/3.x
- OAuth 2.0, MSAL and enterprise API integrations
- Microsoft Graph API — SharePoint, Outlook, Planner, OneDrive
- ServiceNow REST API and Splunk SDK
- Build and maintain LLM/AI agents using LangGraph and LangChain
- ReAct and tool-based agent architectures
- Azure OpenAI/OpenAI integration, prompt engineering and structured outputs
- RAG pipelines, embeddings, hybrid search and reranking
- Vector search using Qdrant/Milvus, including HNSW indexing and filtering
- RAG evaluation using Faithfulness, Relevance, NDCG and MRR
- LLM fine-tuning and neural network/ML model development
- Guardrails, PII redaction, memory, fallback and error-recovery patterns
- Langfuse for tracing, evaluation and prompt management
- Design ETL/ELT pipelines using Prefect
- PostgreSQL, advanced SQL, joins, CTEs and window functions
- Pandas, PyArrow and columnar data processing
- Azure Blob Storage
- Document ingestion/parsing using Docling, Unstructured, python-docx and python-pptx
- Schema evolution, query optimization and warehouse/schema management
- OAuth 2.0 client-credentials flow and token lifecycle
- MSAL and Azure AD app registrations
- Microsoft Graph API integrations with SharePoint, Outlook, Planner and OneDrive
- ServiceNow REST/Table APIs, incident/change management and bulk operations
- Splunk SDK, saved searches, async queries and log analysis
- Pagination and application permissions
- Docker and Linux fundamentals
- Async/concurrent processing, retry/backoff and structured logging/tracing
- Redis pub/sub and TTL
- Nice to have: Ray/distributed execution
- Columnar performance tuning
- Network operations / NOC / alarm correlation knowledge
- IPAM / OTNA integrations
Skills
Required
- Python 3.11
- advanced type hints
- async programming
- LangGraph
- LangChain
- Azure OpenAI / OpenAI APIs
- FastAPI
- REST APIs
- Vector Databases — Qdrant and/or Milvus
- RAG
- prompt engineering
- grounding
Preferred
- Ray/distributed execution
- Columnar performance tuning
- IPAM / OTNA integrations