About Clarity AI
Clarity AI is a global tech company founded in 2017 with a unique mission: bringing societal impact to markets. We leverage AI and machine learning technologies to provide top international investors, governments, companies, and consumers with the right data, methodologies, and tools to make more informed decisions.
About The Role
We are looking for an AI Engineer who thrives at the intersection of rapid experimentation and agile product development. In this role, you will be the bridge between the latest AI developments and tangible product impact. You will be responsible for the "quality loop": moving from a promising proof-of-concept to a highly reliable, optimized, and validated product.
What You’ll Be Doing
- Product-Centric Development: Designing and executing experiments to improve GenAI capabilities, optimizing for user value, reliability, and cost-effectiveness.
- Evaluation Systems: Building the "Golden Path" for quality by designing and implementing robust, multi-dimensional evaluation suites to ensure production readiness.
- Advanced RAG & Reasoning Optimization: Implementing and tuning advanced retrieval strategies (e.g., hybrid search, reranking, agentic retrieval) and optimizing complex reasoning loops.
- Production-Grade Model Tuning: Leading the strategy for supervised fine-tuning (SFT) and Parameter-Efficient Fine-Tuning (LoRA) workflows.
- Performance & Cost Engineering: Balancing the "Quality-Cost-Latency" triangle to maintain high-quality outputs while optimizing token usage.
What You’ll Need
- Applied MLE Background: Proven track record of shipping Machine Learning functionality in a product-focused environment.
- Bleeding-Edge Awareness: Intimate familiarity with trade-offs between frontier models and how to hybridize them for maximum impact.
- Experimental & Analytical Mindset: Experience designing benchmarks, creating "Gold Datasets," and using data to validate improvements.
- Practical LLM Expertise: Deep, hands-on experience with LLM orchestration, vector databases, and evaluation frameworks.
- Technical Stack Mastery: Expert-level Python and experience writing production-grade code.
- Experience: 3+ years of experience in ML or Software Engineering, with at least 2+ years of hands-on experience building and scaling GenAI/LLM-powered features.
- Excellent oral and written English communication skills (minimum C1 level).