We are seeking a skilled Backend + AI Engineer with strong expertise in Large Language Models (LLMs) and vector databases to build and optimize RAG pipelines for financial datasets. The ideal candidate will integrate AI/LLM features into user-facing platforms, ensuring high performance, accuracy, and scalability.

Key Responsibilities :

- Design, build, and optimize retrieval-augmented generation (RAG) pipelines using LLMs and financial datasets.

- Work with vector databases (e.g., FAISS, Pinecone, Weaviate, Qdrant) to build fast and accurate document retrieval systems.

- Fine-tune and integrate open-source and proprietary LLMs (OpenAI, Llama, Mistral, Claude) for domain-specific financial use cases.

- Collaborate with product and engineering teams to integrate AI/LLM features into the platform.

- Evaluate and implement prompt engineering, context compression, and chunking strategies for optimal model

performance.

- Stay updated with latest advancements in Generative AI, NLP, and vector search technologies.

Requirements :

- Strong hands-on experience with LLMs, LangChain, RAG, and prompt engineering.

- Experience working with vector databases like FAISS, Pinecone, or similar.

- Familiarity with retrieval techniques, document embeddings (OpenAI, Hugging Face), and chunking strategies.

- Proficient in Python and AI/ML frameworks (Hugging Face Transformers, OpenAI API).

- Experience with cloud platforms (AWS, GCP, Azure) and deploying scalable AI applications.

- Ability to work independently in a fast-paced startup environment.

Ideal Candidate :

A technically strong AI/LLM engineer with expertise in RAG pipelines, vector search, and LLM fine-tuning, capable of building scalable, high-performance AI features for financial applications, and comfortable working in an agile startup environment.