Job description
Act is building an agent-first mobile communication app and aims to bring intelligence to conversations with minimal prompting. We are hiring a machine learning engineer to develop and optimize models for classification, ranking, and personalization, with a focus on scalable production deployment.
You will work on embeddings, vector search, and hybrid retrieval to improve search relevance, monitor performance, and iterate based on user feedback. Strong Python and PyTorch/JAX skills are essential.
Develop and improve ML models for classification, retrieval, ranking and personalisation. Build classifiers and ranking models optimizing accuracy, latency and cost. Improve search relevance and context retrieval using embeddings and hybrid search. Develop personalization models from user data. Build evaluation pipelines, datasets and metrics to detect regressions. Train, fine-tune and deploy models in production ML pipelines. Monitor performance, debug issues and improve models from feedback. 3+ years of ML engineering experience with production deployments. Strong Python; PyTorch or JAX experience. Solid understanding of ML algorithms, training and evaluation. Experience with classification, ranking, retrieval, or personalization models. Experience building data pipelines and model inference services. Ability to evaluate performance with relevant metrics and experiments. Balance of accuracy, latency, cost, and reliability.