ML инженер

- instinctools is a software development company that provides custom software solutions for businesses of all sizes. The company works closely with clients to understand their specific needs and provide personalized solutions that meet their business requirements.

• Design and build ML models that correct and refine the routing engine’s ETA estimates, utilizing architectures from gradient-boosted trees to neural and Transformer-based models;
• Develop traffic-estimation models that convert large-scale GPS data into road-level speeds and historical-traffic profiles for routing engine integration;
• Work on map-matching to snap noisy GPS data onto road graphs and perform spatial aggregations for modeling;
• Improve ETA calculation, smoothing, and rerouting logic to minimize discrepancies between predicted and actual arrival times;
• Translate routing and ETA goals into ML objectives with appropriate proxy metrics and non-functional requirements;
• Lead end-to-end evaluation, including offline accuracy metrics and online experiments like shadow tests and switchback designs;
• Partner with backend engineers to transition models from prototype to low-latency production serving;
• Collaborate with product and operations teams to turn routing and traffic analysis into concrete features;
• Own the ML lifecycle in production, including serving, monitoring for data and concept drift, and building retraining pipelines.

• 5+ Years of machine learning engineering experience, with at least 3 years focused on building and deploying deep learning models in production;
• Direct experience building regression, forecasting, or other supervised ML systems for real-world problems;
• Expert-level proficiency in Python, core data science libraries, and SQL;
• Ability to design an ML system from scratch, including data analysis, processing, feature engineering, and model serving;
• Experience turning business goals into ML problems with defined proxy metrics and non-functional requirements;
• Experience using MLOps tools and practices to manage the ML model lifecycle;
• Experience deploying models to production on ML serving infrastructure and optimizing for latency;
• Comfort working with large-scale geospatial and behavioral data and distributed processing;
• Upper-Intermediate English;
• Nice to have: Academic background in a quantitative field, subject matter depth in ETA/travel-time prediction or routing-engine quality, hands-on experience with open-source routing engines (Valhalla, OSRM, GraphHopper), experience in mapping/location products, experience building for developing markets, experience with cloud data/ML platforms (BigQuery, Databricks).

• Flexible working time;
• Professional and ambitious team;
• Learning opportunities, seminars, conferences, and time for exploring new technologies;
• Co-funding for English language courses.