About the Role We’re looking for an LLM Engineer to design, build, and scale applications powered by large language models. You’ll work at the intersection of machine learning, software engineering, and product—turning cutting-edge models into reliable, user-facing systems. This role is hands-on, experimental, and impact-driven. If you enjoy rapid prototyping, deep technical problem-solving, and shipping AI features that people actually use, you’ll fit right in. Responsibilities • Design, develop, and deploy LLM-powered applications (chatbots, agents, copilots, RAG systems, etc.) • Fine-tune, prompt-engineer, and evaluate large language models for real-world use cases • Build and optimize retrieval-augmented generation (RAG) pipelines using vector databases • Integrate LLMs into production systems via APIs and microservices • Implement evaluation frameworks for accuracy, safety, latency, and cost • Optimize inference performance, token usage, and system reliability • Collaborate with product, ML, and backend teams to translate business needs into AI solutions • Stay current with advancements in LLMs, tooling, and best practices Required Qualifications • Strong programming skills in Python (and/or TypeScript/JavaScript) • Experience working with LLMs (e.g., OpenAI, Anthropic, Cohere, open-source models) • Solid understanding of prompt engineering, embeddings, and transformers • Experience building RAG systems using vector databases (Pinecone, FAISS, Weaviate, Chroma, etc.) • Familiarity with ML fundamentals and model evaluation techniques • Experience deploying AI systems in production (cloud, APIs, monitoring) • Strong problem-solving skills and ability to work in fast-moving environments Preferred / Nice to Have • Experience fine-tuning open-source models (LLaMA, Mistral, Mixtral, etc.) • Knowledge of ML frameworks (PyTorch, TensorFlow, Hugging Face) • Experience with agent frameworks (LangChain, LlamaIndex, AutoGen, etc.) • Understanding of AI safety, hallucination mitigation, and guardrails • Background in backend engineering or distributed systems • Experience with cost optimization and scaling AI workloads