Overview
On Site
Depends on Experience
Full Time
Skills
RAG
LLM
Python
Job Details
Role Overview:
As an LLM Engineer, you will be a key part of a GenAI transformation program, building intelligent, scalable LLM-powered solutions that enhance internal productivity, customer experiences, and operational decision-making. You will partner with business stakeholders, product owners, and data scientists to design and deploy use-case driven GenAI applications using Large Language Models and vector databases.
Key Responsibilities:
- Design, fine-tune, and deploy LLM-based applications and copilots tailored for retail business workflows (e.g., customer service, merchandising, catalog intelligence).
- Evaluate, prompt, and orchestrate LLM APIs (OpenAI, Anthropic, Mistral, etc.) in enterprise-ready environments.
- Build secure RAG (Retrieval-Augmented Generation) pipelines using enterprise-grade unstructured content.
- Integrate vector databases (e.g., FAISS, Weaviate, Milvus, Pinecone) for semantic search and context injection.
- Develop backend services (Python/FastAPI/Flask) for scalable LLM app deployment.
- Collaborate with DevOps/Data Engineers to deploy LLM workloads in cloud/on-prem environments (Azure/Google Cloud Platform).
- Ensure enterprise compliance on data security, PII masking, token limits, audit logging, and rate-limiting.
- Tune performance using evaluation frameworks like RAGAS, Promptfoo, LLM Benchmarks, etc.
- Translate business use cases into rapid LLM POCs and scale MVPs to production.
Required Technical Skills:
- Strong programming in Python with experience in LangChain, LlamaIndex, or Haystack.
- Proven experience with OpenAI, Azure OpenAI, Cohere, or other LLM APIs.
- Proficiency in vector database integration: FAISS, Weaviate, Milvus, or Pinecone.
- Understanding of prompt engineering, prompt chaining, function calling, and tool use with LLMs.
- Familiarity with REST APIs, FastAPI, and containerization (Docker, Kubernetes).
- Good grounding in MLOps/DevOps for deploying models in secure environments.
- Working knowledge of front-end integration (React/Streamlit) is a plus.
Preferred Qualifications:
- 5 8 years of experience in AI/ML/NLP with 1+ years focused on LLMs.
- Experience working in the retail domain or building GenAI solutions for enterprise clients.
- Exposure to unstructured document processing, OCR, or knowledge extraction is a plus.
- Bachelor's or Master's in Computer Science, AI, Data Science, or related field.
Employers have access to artificial intelligence language tools (“AI”) that help generate and enhance job descriptions and AI may have been used to create this description. The position description has been reviewed for accuracy and Dice believes it to correctly reflect the job opportunity.