Role Overview
Build and deploy generative AI solutions using LLM fine-tuning, RAG architectures, and agentic AI systems.
Responsibilities
- Fine-tune large language models for domain-specific applications and use cases
- Design and implement RAG (Retrieval Augmented Generation) pipelines with vector databases
- Build agentic AI systems with autonomous decision-making and tool-using capabilities
- Optimize LLM performance through prompt engineering, parameter tuning, and model selection
- Develop and deploy production-ready GenAI applications and APIs
- Evaluate model performance, conduct A/B testing, and iterate on solutions
- Collaborate with cross-functional teams to integrate GenAI into products
Requirements
- Bachelor's degree in Computer Science, Engineering, AI/ML, or related field
- Strong experience with LLM fine-tuning (LoRA, QLoRA, full fine-tuning, PEFT methods)
- Proven expertise building RAG systems with vector databases and embeddings
- Hands-on experience developing agentic AI solutions and multi-agent systems
- Proficiency with LLM frameworks (LangChain, LlamaIndex, Haystack)
- Experience with vector databases (Pinecone, Weaviate, ChromaDB, FAISS)
- Strong Python programming skills
- Understanding of transformer architectures and LLM APIs
Preferred
- Experience with distributed training and GPU optimization
- Knowledge of MLOps, model deployment, and monitoring
- Familiarity with Hugging Face ecosystem
- Experience with prompt optimization and evaluation frameworks
- Understanding of LLM safety, alignment, and guardrails
- Background in NLP or deep learning research
