Role Overview
We are looking for a motivated Applied GenAI Engineer to build AI-powered applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agent-based workflows. The role involves working with Python, LangChain, and LangGraph to develop practical AI solutions and solve real-world business problems.
Responsibilities
- Develop AI applications using Python and LLMs.
- Build RAG pipelines involving document loading, chunking, embeddings, and vector search.
- Develop LLM workflows, chains, and tool integrations using LangChain.
- Build multi-step workflows and AI agents using LangGraph.
- Integrate LLM APIs and external services.
- Test, evaluate, debug, and improve AI applications.
- Take end-to-end ownership of application development and delivery.
Requirements
- Hands-on experience with Python, including functions, classes, data structures, and exception handling.
- Practical experience with LLMs and prompt engineering.
- Experience building RAG applications.
- Hands-on experience with LangChain and/or LangGraph.
- Knowledge of embeddings, token management, and context windows.
- Experience integrating REST APIs and external services.
- Knowledge of MySQL or other relational databases and SQL queries.
- Strong troubleshooting and problem-solving skills.
Nice to Have
- Experience with vector databases, Elasticsearch, or OpenSearch.
- Familiarity with Hugging Face and embedding models.
- Knowledge of reranking techniques and conversational memory.
- Experience with FastAPI, Git, Docker, and deployment.