Solvex Solutions
Website:
solvex-solutions.com
Job details:
Job Title: AI/LLM Engineer (RAG & Fine-Tuning)
Work Mode: Remote (Contract- 6 Months)
Job Summary:
We are looking for a highly skilled AI/LLM Engineer to design, build, and optimize advanced Large Language Model (LLM) applications. The ideal candidate will have strong expertise in Retrieval-Augmented Generation (RAG), prompt engineering, and LLM evaluation frameworks. You will work on building intelligent systems that leverage structured and unstructured data to deliver high-quality, context-aware outputs.
Key Responsibilities:
- Design and implement scalable RAG architectures for enterprise AI applications
- Develop and optimize chunking strategies, embeddings, and vector database pipelines
- Build and fine-tune LLM-based applications using modern frameworks
- Apply advanced prompt engineering techniques (few-shot, chain-of-thought, system prompts)
- Develop and maintain evaluation frameworks to measure LLM performance and accuracy
- Optimize search and retrieval mechanisms for latency and relevance
- Work with cross-functional teams to integrate AI solutions into production systems
- Experiment with fine-tuning and model adaptation techniques
Required Skills (Must Have):
- Strong hands-on experience with RAG architecture
- Expertise in:
1. Chunking strategies
2.Embeddings
3.Vector databases (e.g., FAISS, Pinecone, Weaviate)
- Advanced prompt engineering
1.Few-shot prompting
2.Chain-of-thought reasoning
3.System role design
- Experience building LLM evaluation frameworks
- Strong programming skills in Python
- Hands-on experience with LangChain or similar LLM orchestration frameworks
- Experience in search & retrieval optimization
Nice to Have:
- Experience building LLM-driven coaching or conversational workflows
- Exposure to fine-tuning open-source or proprietary LLMs
Experience:
- 3–8 years of experience in AI/ML, NLP, or related fields
Education:
- Bachelor’s/Master’s degree in Computer Science, AI, Data Science, or related field
Click on Apply to know more.