remote
AI/ML Engineer - The Algorithm
ML Engineer
AI/ML Engineer focused on building and deploying generative AI solutions, designing RAG pipelines, and integrating LLMs with web applications using LangChain and vector databases.
About the role
Key Responsibilities
- Develop and deploy AI/ML and generative AI solutions that meet business objectives.
- Build, tune, and maintain Retrieval‑Augmented Generation (RAG) pipelines for scalable knowledge retrieval.
- Design and implement AI applications using LangChain and large language model frameworks.
- Implement and fine‑tune NLP models for advanced text processing and analysis.
- Integrate AI models with web services and APIs, ensuring robust performance and security.
- Manage vector databases and embedding models to support high‑throughput inference.
Requirements
- Proven experience with generative AI, LLMs, and RAG architectures.
- Strong background in NLP, including tokenization, embeddings, and model fine‑tuning.
- Hands‑on expertise with LangChain, vector databases (e.g., Pinecone, Weaviate), and embedding libraries.
- Solid programming skills in Python and familiarity with cloud AI services.
- Excellent problem‑solving abilities and a passion for building production‑ready AI solutions.
Skills
generative ailangchainnlp