Binance Accelerator Program LLM Recommendation & Agentic AI Engineer
Job Summary
- Design and develop LLM-powered recommendation and personalization systems including candidate generation ranking reranking user intent understanding and context-aware recommendation for financial and Web3 scenarios.
- Explore and build agentic AI systems that leverage internal data APIs tools and domain-specific capabilities to perform complex financial and trading-related tasks.
- Develop and optimize tool routing tool retrieval planning and multi-step reasoning mechanisms enabling LLM agents to efficiently select and utilize the appropriate capabilities from a large-scale tool ecosystem.
- Perform post-training of large language models including SFT preference optimization reinforcement learning and other techniques to improve recommendation quality tool-use accuracy reasoning capability and task completion performance.
- Build and maintain high-quality training and evaluation datasets benchmarks and evaluation pipelines for LLM recommendation and agentic systems covering dimensions such as relevance personalization tool selection task success rate latency and reliability.
- Prototype and iterate on LLM / Agent workflows including retrieval recommendation planning execution verification memory and feedback loops and integrate successful prototypes into production systems.
- Explore the application of small and specialized language models for routing recommendation classification reranking and other latency-sensitive tasks balancing model quality inference cost and system performance.
- Work closely with senior engineers researchers product teams and domain experts to complete system design experimentation integration deployment and continuous optimization.
Strong foundation in machine learning NLP information retrieval recommendation systems or large language models.
- Hands-on experience with at least one of the following areas:
1. Large Language Models and post-training
2. Recommendation systems / ranking / retrieval
3. LLM agents and tool-use systems
4. Retrieval-Augmented Generation (RAG)
5. Reinforcement Learning or preference optimization
- Familiar with modern LLM techniques such as SFT RL DPO/GRPO-style optimization prompt engineering structured generation function/tool calling and model evaluation.
- Good understanding of recommendation or search techniques such as embedding-based retrieval learning-to-rank reranking personalization user modeling or generative recommendation.
- Strong programming skills in Python and experience with deep learning frameworks such as PyTorch.
- Ability to conduct experiments independently analyze model/system performance and translate research ideas into practical production solutions.
- Experience building production-scale recommendation search or LLM systems.
- Experience with agent frameworks tool routing multi-agent systems memory systems or long-horizon agent workflows.
- Experience with LLM inference and serving frameworks such as vLLM SGLang TensorRT-LLM or equivalent systems.
- Familiarity with Web3 cryptocurrency financial markets or trading systems.
- Experience working with large-scale datasets distributed training model serving or high-throughput online systems.
- Publications open-source contributions or practical projects related to LLMs recommendation systems agents search or reinforcement learning are a plus.
Shape the future with the worlds leading blockchain ecosystem
Collaborate with world-class talent in a user-centric global organization with a flat structure
Tackle unique fast-paced projects with autonomy in an innovative environment
Thrive in a results-driven workplace with opportunities for career growth and continuous learning
Competitive salary and company benefits
Work-from-home arrangement (the arrangement may vary depending on the work nature of the business team)
Binance is committed to being an equal opportunity employer. We believe that having a diverse workforce is fundamental to our success.
By submitting a job application you confirm that you have read and agree to our Candidate Privacy Notice.
We may use artificial intelligence (AI) tools to support parts of the hiring process such as reviewing applications analyzing resumes or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed please contact us.
Required Experience:
Unclear Seniority
About Company
Binance is a blockchain ecosystem comprised of Exchange, Labs, Launchpad, Info, Academy, Trust Wallet, and Blockchain Charity Foundation (BCF). Binance Exchange is one of the fastest and most popular cryptocurrency exchange platforms in the world, capable of processing over 1.4 millio ... View more