Logo
Mindlance

Artificial Intelligence Engineer

Mindlance, Charlotte, North Carolina, United States, 28245

Save Job

Overview This role focuses on building, fine-tuning, and deploying Large Language Model (LLM)-based applications using frameworks like LangChain and LangGraph.

Base pay range:

$70.00/hr - $75.00/hr

Location: Charlotte, NC; Chandler, TX; Irving, TX

Duration: 24 months Contract

Only W2, No C2C

Key Responsibilities

Prompt Engineering / Optimization

Crafting and refining prompts and context windows to improve model accuracy, relevance, and consistency.

Experimenting with few-shot and chain-of-thought prompting.

Managing token usage and response quality trade-offs.

LLM Integration (LangChain / LangGraph)

Developing pipelines and agent frameworks that orchestrate LLM calls.

Building modular components like retrievers, memory, and custom tools.

Integrating with vector databases (e.g., FAISS, Chroma, Pinecone) for retrieval-augmented generation (RAG).

Using pre-trained models (e.g., GPT, LLaMA, Mistral, Falcon, etc.) and adapting them to domain-specific datasets.

Training with libraries such as Hugging Face Transformers, PEFT, or LoRA.

Evaluating model performance and running inference benchmarks.

Python Development

Writing efficient Python code for model orchestration, data preprocessing, and pipeline automation.

Working with APIs, REST endpoints, or SDKs to integrate LLM outputs into applications.

Seniority Level Mid-Senior level

Employment Type Contract

Job Function Banking, Technology, Information and Media, and Financial Services

EEO Statement Mindlance is an Equal Opportunity Employer and does not discriminate in employment on the basis of Minority/Gender/Disability/Religion/LGBTQI/Age/Veterans.

#J-18808-Ljbffr