About the Role
We are looking for an AI/ML Engineer to join our team and build and improve the intelligence layer of our platform. You will design and orchestrate AI workflows that combine live web research, LLMs, and machine learning models to generate insights. This is a hands-on engineering role — you will design prompts, build async pipelines, train and deploy ML models, and ship production features end to end.
What You’ll Do
- Design, build, and orchestrate AI workflows that combine live web search, LLM scoring, and structured reasoning pipelines
- Build and tune prompt systems for structured LLM outputs — scoring rubrics, reasoning generation, hallucination prevention
- Train, evaluate, and improve ML/deep learning models for prediction tasks using structured data
- Deploy ML models to production as inference endpoints/services, manage versioning and rollback, and continuously monitor model performance (drift, accuracy decay, data quality) — retraining and updating models as needed
- Build async data collection pipelines that gather data from external sources in real time
- Monitor LLM behavior in production using observability tooling and continuously improve prompt quality
- Design scoring systems that are explainable and consistent
- Improve data quality by building smart deduplication, classification, and validation logic
What We’re Looking For
- Strong Python skills — async/await, asyncio, production-quality code
- Experience working with LLM APIs and prompt engineering
- Understanding of ML/deep learning fundamentals — feature engineering, model training, evaluation, hyperparameter tuning
- Experience with gradient boosting models (e.g., CatBoost, XGBoost, LightGBM) for prediction tasks
- Experience with MLOps — deploying models to production, versioning, and monitoring model performance over time
- Experience with web scraping and data extraction at scale
- Comfortable working with relational databases and async database drivers
- Strong debugging skills — you can trace a bug through a multi-step async pipeline
- Product sense — you understand that AI outputs need to be explainable and trustworthy to end users
Nice to Have
- Experience with deep learning frameworks (e.g., PyTorch, TensorFlow)
- Experience fine-tuning and serving transformer-based models
- Familiarity with RAG (Retrieval-Augmented Generation) systems
- Experience with AWS RDS, S3, and SageMaker
- Experience with hyperparameter optimization frameworks
