Summary You are part of the Technical Intelligence (TechInt) team. The team’s main function is to recon the blockchain industry and feed the company with new trends and projects. The TechInt team has automatized the recon process by utilizing a data lake and machine learning. You will increase the capabilities of our automated system by exploiting large language models (LLMs). You integrate LLMs into our recognition processing pipeline. You enable the exploration of data insights through the question-answer capabilities of LLMs. You work closely with leadership to understand and define requirements. You ensure alignment with the department’s strategy and roadmap. You work together with a Data Scientist and an Intelligence Engineer to implement the LLM pipeline. You ensure the LLM systems are functional and available. Duties Set up scriptable AI agents (e.g., AutoGPT, Jarvis) to surf and scrape textual signals from the web. Fine-tune (augment) an LLM model with support of open source tooling such as Langchain and Vectorized Databases. Use LLMs to solve topic classification, trends detection, and causal analysis. Use related Machine Learning techniques (e.g., regression, ensemble methods, time-series) for forecasting capabilities. Set up a chatbot web interface linked to generative question answering LLM. Productionize the LLM/NLP models by architecting control flows covering all sub-systems from data to deployment. Requirements Key competencies Expert in the English language (vocabulary, tenses, clarity, conciseness) for efficient LLM prompts engineering. Good foundation in Machine Learning (ML), Natural Language Processing (NLP), and Deep Learning (DL). Solid knowledge of Python’s data stack with a focus on NLP: Spark, Spark-NLP, Regex, Pandas, Polars, Tensorflow, Pytorch, SpaCy, Huggingface. Solid programming skills covering algorithms, data structures, and design patterns. Solid software development practices covering version control, testing, and continuous integration. Knowledge of the Blockchain domain and passionate about gaining further breadth and depth of the domain. Education/Experience BSc/MSc in Computer Science or a related field, preferably with a focus on NLP, AI, or ML. 5+ years of work experience in engineering ML or AI solutions. Experience with cloud platforms, preferably Databricks and AWS. Experience with LLM toolstack, for example : Openai API, Auto-GPT, Langchain, Llamaindex, Chromadb, or other vector databases. Experience with AutoML frameworks. Personal Github repository with proven experience in coding LLM/NLP/ML/AI projects. Benefits Location IOG is a fully distributed organization but due to team distribution, we require someone to be based either in Ireland, the UK or Poland. All colleagues Flexible schedule Remote work Laptop reimbursement New starter package to buy hardware essentials (headphones, monitor, etc) Learning Development opportunities Competitive PTO and Sick Leave plan UK Ireland Employees Monthly Health Stipend to use towards any wellness or medical coverage/service Pension At IOG, we value diversity and always treat all employees and job applicants based on merit, qualifications, competence, and talent. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
https%3A%2F%2Fremotive.com%2Fremote-jobs%2Fsoftware-dev%2Fllm-engineer-1843756