Experience:

• Proven experience building and deploying agentic and RAG-based applications in production
• Ability to optimize retrieval pipelines for large datasets (3M+ rows)
• Hands-on experience building LLM agents across platforms such as Gemini, OpenAI, and Claude
• Experience fine-tuning open-source LLMs using LoRA or similar techniques
• Deployment experience with cloud platforms (AWS, GCP, Azure), containerization (Docker, Kubernetes), and inference servers (vLLM)
• Expert-level proficiency in Python and ML frameworks like PyTorch or TensorFlow

Qualification:

• Advanced degree (M.S. or Ph.D.) in Computer Science, Engineering, or a related quantitative field

Responsibilities:

• Develop end-to-end RAG applications from data ingestion to real-time delivery
• Optimize retrieval pipelines to handle millions of rows with minimal latency
• Design and implement intelligent agents capable of complex decision-making using LLMs
• Enhance product data by extracting descriptive tags from images
• Prepare and clean catalog data for integration with LLM applications
• Collect and process product and review data from social platforms
• Set up hyperparameter optimization workflows for machine learning pipelines
• Fine-tune and adapt models to improve performance on domain-specific tasks
• Collaborate with data scientists and engineers to deploy LLM applications into production
• Implement MLOps best practices for continuous integration, deployment, and monitoring
• Stay updated on advancements in LLM architectures, agentic frameworks, and RAG methodologies

Nice to have:

• Experience with distributed computing frameworks such as Spark or Ray for processing large-scale datasets

More skills:

RAG-based applications, Retrieval pipelines, TrinoDB, Scala REPL, Multimodal tasks, ChromaDB, Pinecone, Weaviate, Cloud platforms, AWS, GCP, Azure, Docker, Kubernetes, PyTorch, TensorFlow

Other:

• Full-Time
• On-site