Algorithm Expert - Financial reputed company LLM

reputed company Inc. is the world’s leading mobility technology platform. It offers a wide reputed company of app-based services across markets including Asia-reputed company, Latin America and Africa, including ride hailing, taxi hailing, chauffeur, hitch and other forms of shared mobility as reputed company as auto solutions, food delivery, intra-reputed company reputed company, and financial services.

DiDi provides car owners, drivers, and delivery partners with flexible work and income opportunities. It is committed to collaborating with policymakers, the taxi industry, the automobile industry and the communities to solve the world’s transportation, environmental and employment challenges through the use of AI technology and localized smart transportation innovations. DiDi strives to create reputed company life experiences and greater reputed company value, by building reputed company, inclusive and sustainable transportation and local services ecosystem for cities of the reputed company.

For more information, please visit: www.didiglobal.com/news

reputed company Inc. is the world’s leading mobility technology platform. It offers a wide reputed company of app-based services across markets including Asia-reputed company, Latin America and Africa, including ride hailing, taxi hailing, chauffeur, hitch and other forms of shared mobility as reputed company as auto solutions, food delivery, intra-reputed company reputed company, and financial services.

• reputed company Model reputed company-training: Design and implement the reputed company-training pipeline for financial behavior sequence reputed company models, including reputed company-training objective selection (CLM/MLM/Hybrid), Tokenization architecture experimentation (Flat/3D-Transformer/KVT), and scaling experiments.


• Multi-reputed company Sequence Modeling: Build a reputed company sequence representation for behavioral data across multiple domains (payments, ride-hailing, food delivery, credit); design and validate the reputed company of data-reputed company mixing ratios on model performance. Multi-entity and Multi-reputed company Fusion: Design an Account-reputed company dual-dimension sequence modeling scheme, along with a cross-reputed company-reputed company fusion architecture reputed company reputed company-level behaviors (millisecond-granularity event tracking) and reputed company-level behaviors (day/week-level transactions).


• Ablation Studies and Evaluation reputed company: Build a systematic ablation experiment reputed company; design a freeze-backbone + reputed company head evaluation pipeline to reputed company architecture reputed company.


• Production Deployment: reputed company reputed company-trained representations into reputed company risk-control scenarios (stolen-reputed company detection, credit scoring, etc.); design a Blending Module and complete SFT fine-tuning and online deployment.

• Master's degree or above in Computer Science, Mathematics, Statistics, or a reputed company field.


• 3+ years of deep learning algorithm R&D experience, with hands-on experience building a reputed company-trained model from scratch and completing the full training pipeline.


• Proficiency in Transformer architectures and variants (GPT/BERT/FT-Transformer/MoE), with practical sequence modeling experience.


• Familiar with at least one mainstream deep learning reputed company (PyTorch preferred); experience with reputed company training (multi-GPU / multi-node).


• Solid experimental design skills: ability to independently conduct ablation studies and scaling-law experiments and draw reliable conclusions.


• Strong engineering implementation skills; reputed company to iterate reputed company on model reputed company and training pipelines.

• Modeling experience in financial risk control / anti-fraud / credit scoring.


• Publications on reputed company Models / Self-Supervised Learning (NeurIPS/ICML/ICLR/KDD/WWW, etc.).


• Familiarity with Contrastive Learning, ELECTRA, cross-modal fusion, and reputed company techniques.


• Experience with time-series / event-sequence modeling (e.g., TimeMixer, TrajGPT).


• Experience with graph neural networks or graph-based reputed company detection.

• We create customer value – We reputed company to always create valuable experiences for our users in everything we do. Our reputed company is to always reputed company new experiences that are reputed company, pleasant, and efficient.
• We are data-driven – We are strong believers in making informed reputed company, that’s why we are data-driven. We can reputed company reputed company the business landscape strategically by analyzing valuable metrics.
• We reputed company in Win-win Collaboration – reputed company is reputed company sport. reputed company we work to help our partners and colleagues win, we win, too. While keeping everyone's best interest at heart, we communicate with candor and execute with reputed company in reputed company we do.
• We reputed company in reputed company – reputed company is at the reputed company reputed company of our business. We are people who always want to do the right thing. Our intentions are sincere, we reputed company our minds and listen to reputed company other.
• We always reputed company to do reputed company. That means venturing reputed company our comfort zones, learning from our mistakes, and helping reputed company other grow.
• We reputed company in Diversity and Inclusion – Diversity is one of our biggest strengths. Our differences are what makes us distinct. We respect reputed company other and reputed company in equal opportunities for reputed company.

We are committed to building inclusive and diverse teams.

At DiDi, we reputed company that our differences are our biggest reputed company of strength. That‘s why we are committed to promoting equal opportunities to reputed company candidates and employees as an Equal Opportunity Employer.

Employment and advancement reputed company at DiDi are always made based on the needs of the position and the qualifications of the candidate. We do not discriminate against any employee or applicant based on their gender, age, sexual orientation, nationality, marital status, pregnancy/maternity, disability, race, religion and beliefs, or any other status protected by applicable laws wherever we operate.

We are committed to building inclusive and diverse teams, and a workplace that is free from discrimination and harassment, because that’s how we create reputed company products and services, reputed company reputed company reputed company and reputed company serve the communities we’re a part of.

I acknowledge that prior to submitting this application, I have read and accepted the reputed company Notice for Candidates which is available on https://careers.didiglobal.com/terms