TekValue IT Solutions
AI Engineer (LLM Fine-Tuning & RAG Architecture)
TekValue IT Solutions, Wilmington, Delaware, us, 19894
Job Description – AI Engineer (LLM Fine-Tuning & RAG Architecture)
Experience Required: 5–7 Years (including 1–2 years of real‑time AI LLM work)
Role Overview INCYTE CORP is seeking a skilled AI Engineer with hands‑on experience in Large Language Model (LLM) fine‑tuning, Retrieval‑Augmented Generation (RAG), and applied AI architecture. The ideal candidate will possess a strong foundation in machine learning, NLP, and data engineering, with proven experience deploying AI solutions that enhance business decision‑making and automation.
Key Responsibilities
Design, build, and implement LLM fine‑tuning pipelines using frameworks such as Hugging Face Transformers, LangChain, or OpenAI API.
Develop and optimize RAG architectures integrating external knowledge bases, vector databases (e.g., FAISS, Pinecone, Chroma), and embeddings.
Collaborate with data scientists and engineers to train and evaluate models for text summarization, question‑answering, and contextual retrieval.
Implement prompt‑engineering and model‑evaluation strategies to improve response accuracy, latency, and reliability.
Maintain and monitor AI pipelines in production; handle model versioning, retraining, and scalability.
Work closely with client stakeholders to translate business requirements into technical solutions.
Document all workflows and ensure compliance with data privacy and security standards.
Required Skills & Qualifications
Bachelor’s / Master’s degree in Computer Science, AI, Data Science, or related field.
5–7 years of overall IT experience with 1–2 years in AI model development or deployment.
Strong knowledge of RAG architecture design and vector database integration.
Proficiency in Python, LangChain, Transformers, and PyTorch or TensorFlow.
Familiarity with cloud AI platforms (Azure OpenAI, AWS SageMaker, GCP Vertex AI).
Experience in API development, Docker/Kubernetes, and CI/CD for AI models.
Excellent communication skills and ability to work in a collaborative, client‑facing environment.
Preferred (Plus Points)
Experience with enterprise RAG or multi‑agent AI systems.
Understanding of MLOps workflows and model observability tools.
Contributions to open‑source LLM projects or AI research.
#J-18808-Ljbffr
Role Overview INCYTE CORP is seeking a skilled AI Engineer with hands‑on experience in Large Language Model (LLM) fine‑tuning, Retrieval‑Augmented Generation (RAG), and applied AI architecture. The ideal candidate will possess a strong foundation in machine learning, NLP, and data engineering, with proven experience deploying AI solutions that enhance business decision‑making and automation.
Key Responsibilities
Design, build, and implement LLM fine‑tuning pipelines using frameworks such as Hugging Face Transformers, LangChain, or OpenAI API.
Develop and optimize RAG architectures integrating external knowledge bases, vector databases (e.g., FAISS, Pinecone, Chroma), and embeddings.
Collaborate with data scientists and engineers to train and evaluate models for text summarization, question‑answering, and contextual retrieval.
Implement prompt‑engineering and model‑evaluation strategies to improve response accuracy, latency, and reliability.
Maintain and monitor AI pipelines in production; handle model versioning, retraining, and scalability.
Work closely with client stakeholders to translate business requirements into technical solutions.
Document all workflows and ensure compliance with data privacy and security standards.
Required Skills & Qualifications
Bachelor’s / Master’s degree in Computer Science, AI, Data Science, or related field.
5–7 years of overall IT experience with 1–2 years in AI model development or deployment.
Strong knowledge of RAG architecture design and vector database integration.
Proficiency in Python, LangChain, Transformers, and PyTorch or TensorFlow.
Familiarity with cloud AI platforms (Azure OpenAI, AWS SageMaker, GCP Vertex AI).
Experience in API development, Docker/Kubernetes, and CI/CD for AI models.
Excellent communication skills and ability to work in a collaborative, client‑facing environment.
Preferred (Plus Points)
Experience with enterprise RAG or multi‑agent AI systems.
Understanding of MLOps workflows and model observability tools.
Contributions to open‑source LLM projects or AI research.
#J-18808-Ljbffr