Ai Engineer - Remote

- Build an LLM-Powered Insights Engine: Design, build, and deploy a
Retrieval-Augmented Generation (RAG) pipeline to provide real-time market insights on
logistics quotes. You will use vetted data sources to ground LLM responses, preventing
hallucinations and ensuring accuracy.
- Develop Predictive ETA Models: Create and train machine learning models (e.g., using
XGBoost or LightGBM) to predict shipment transit times. Your work will shift our
platform from using deterministic carrier ETAs to providing a more realistic, probabilistic
forecast with confidence intervals (e.g., "80% probability of arrival between August 26th
and 30th").
- Engineer Data & Features: Develop and maintain robust ETL/ELT data pipelines to
aggregate, clean, and standardize historical shipment data from our Elasticsearch data
lake. You will be responsible for feature engineering to create the inputs for your models
(e.g., carrier, lane, seasonality, transshipment flags).
- Create High-Performance APIs: Build and maintain scalable, low-latency APIs, using
FastAPI, to serve AI-driven insights, summaries, and predictions to our frontend
applications.
- Implement Explainable AI (XAI): Integrate frameworks like SHAP to provide customers
with simple, human-readable explanations for AI predictions (e.g., "A 3-day delay is
predicted due to seasonal port congestion").
- Collaborate and Deploy: Work closely with product, frontend, and platform teams to
design, iterate on, and deploy these features into production, ensuring they are robust,
scalable, and valuable to the end-user.

(Required Skills)
- Proven Experience: A strong track record as a Machine Learning Engineer or Data
Scientist with significant software engineering skills.
- Python Expertise: Mastery of Python and its core data science and ML ecosystem
(e.g., pandas, scikit-learn, numpy).
- LLM & RAG Experience: Hands-on experience building applications with Large
Language Models, specifically implementing Retrieval-Augmented Generation (RAG)
pipelines and working with vector databases.
- Classical ML Proficiency: Strong experience with gradient boosting models (XGBoost,
LightGBM) and other regression/classification techniques.
- API Development: Demonstrable experience building and deploying production-ready
APIs, with a strong preference for FastAPI.
- Data & Databases: Proficiency in querying and managing data in large-scale data
stores, specifically Elasticsearch. Experience with data lakes and building ETL/ELT
pipelines is essential.
- Problem-Solving Mindset: You are passionate about translating complex business
problems into concrete, data-driven technical solutions.

Bonus Points (Highly Valued Skills)
- Time-Series Forecasting: Experience with time-series analysis and forecasting models.
- MLOps: Familiarity with MLOps practices for model deployment, monitoring, and
lifecycle management (e.g., CI/CD for models, versioning, performance tracking).
- Explainable AI (XAI): Practical experience with SHAP, LIME, or similar XAI frameworks.
- Domain Knowledge: Experience in the logistics, shipping, or supply chain industry is a
massive plus. Familiarity with concepts like GRI, ETD/ETA, or UN/LOCODEs data would
be highly beneficial.

- Receive 100% salary from the onboarding date.
- Participate in company activities: quarterly team building, travel, vacation and other activities.
- Work with large and advanced systems, have the opportunity to develop comprehensive technology skills with complex problems, requiring high accuracy.