Overview
Skills
Job Details
Key Responsibilities:
Design and implement RAG pipelines combining vector search, embedding models, and LLMs.
Integrate and fine-tune LLMs for domain-specific tasks.
Develop and maintain Python-based ML services and APIs.
Work closely with internal stakeholders to translate business problems into GenAI solutions.
Evaluate and optimize model performance and retrieval quality.
Requirements: 5 8 years of experience in software development with strong Python skills.
Practical experience with LLMs, RAG Architecture, and ML Frameworks (e.g., Hugging Face, LangChain, FAISS, Scikit-learn, etc.).
Solid understanding of embedding techniques, prompt engineering, and model deployment.
Familiarity with cloud services (e.g., Azure, AWS, or Google Cloud Platform).