AI / LLM Engineer – OrcaWorks AI

OrcaWorks AI is hiring an AI/LLM Engineer to integrate intelligent models into production systems. The role focuses on developing, fine-tuning, and evaluating LLMs for business automation, implementing RAG and prompt engineering pipelines, and collaborating on backend services.

• Develop, fine-tune, and evaluate LLMs for business and workflow automation. Implement prompt engineering, RAG, and context-aware AI pipelines. Integrate with agent frameworks like AutoGen, LangChain, and CrewAI. Collaborate with backend teams on FastAPI-based services. Conduct model performance analysis and error tracking. Explore and operationalize open-source models (Llama, GPT, Mistral) in production.

• Master's degree (or Bachelor's with equivalent experience) in AI, CS, or ML. Strong grasp of transformer architectures, embeddings, and NLP. Hands-on experience with Hugging Face Transformers, LangChain, and vector databases (Vespa, Pinecone, FAISS). Familiarity with FastAPI, SQLModel, and MLOps tools. Programming experience in Python (PyTorch/TensorFlow).