Generative AI Engineer
Plano, TX (hybrid- 3 days per week in their Plano, TX office).
LOCAL CANDIDATES ONLY PLEASE -Candidates must reside local to the Dallas area. The client is not accepting candidates willing to relocate
6+ Months (PTE)
No H1B and CPT
Telecommunication
The final interview is a mandatory interview in Plano TX.
Responsibilities:
Provide hands-on experience building, deploying, and maintaining applications using LangChain and LangGraph frameworks.
Provide LLM fine tuning
Prompt Engineering: Design, test, and optimize prompts for generative models to achieve desired outputs.
Graph-Based Workflow Design: Architect, implement, and debug complex, stateful, branching conversational flows using LangGraph.
API Development & Integration: Integrate external APIs, tools, and data sources into AI-driven workflows.
Productionize AI/ML or LLM-powered workflows (using LangGraph, LangChain, CrewAI etc.) with a focus on reliability, reproducibility, and auditability
Required Skills:
In-depth understanding and practical experience with Large Language Models (LLMs) such as OpenAI GPT-3/4, Anthropic Claude, Meta Llama, or similar.
Familiarity with ML/AI libraries such as PyTorch, TensorFlow, Hugging Face Transformers, or similar.
Hands-on experience in Python, Pyspark/Spark, NO-SQL (MongoDB), SQL- PostgreSQL, Redis, Databricks, Delta Lake, Azure Cloud
Advanced proficiency in Python, including experience with asynchronous programming, data structures, and object-oriented design.
DS/ML algorithms and model working knowledge - XGBoost, Linear Regression, Clustering, Decicion Tree, KNN, SVN, etc.
Strong understanding of LLMOps fundamentals, including prompt/model/config versioning and traceable run metadata.