LLM Engineer

Trustana is seeking an LLM Engineer to join their team and enhance their SaaS platform with AI features. The role involves applying large language models to automate product data management for retailers, brands, and distributors, while also mentoring teammates and guiding technical direction at a senior level. Responsibilities: Research, prototype, and productionize LLM solutions for tasks such as product classification, enrichment, and workflow automation; Fine-tune and optimize foundation models for domain-specific performance; Build scalable inference pipelines and APIs to deliver AI features in production; Partner with backend, data, and product teams to define Qualifications: L3: 3–5 years of software engineering or applied ML experience, with direct exposure to LLMs; L4: 5–8 years of engineering experience, with a proven track record of building and deploying LLM systems in production; Strong coding skills in Python and familiarity with ML frameworks (PyTorch, TensorFlow); Hands-on experience with fine-tuning, prompting, or integrating LLMs (OpenAI, Anthropic, Hugging Face, Qwen, etc.); Knowledge of data pipelines, embeddings, vector databases (e.g., Pinecone, Weaviate, FAISS), and retrieval-augmented generation (RAG); Experience deploying ML models as APIs or services in a cloud environment (AWS Required Skills: Python, Machine Learning, LLM, PyTorch, TensorFlow, Fine-tuning, Data Pipelines, Embeddings, Vector Databases, AWS, APIs, Generative AI