Senior Software Engineer, EvolutionIQ

• As an ambitious Senior AI/LLM Engineer, you will play a key role in advancing our industry-leading medical synthesis product
• You take strong ownership of your work and have a proven track record of driving projects end-to-end, from ideation through deployment
• Thriving in a fast-paced startup environment, you stay current with the latest AI and machine learning research
• You’re passionate about applying hybrid approaches that combine large language models (LLMs), statistical machine learning techniques, and retrieval-augmented generation (RAG) with embeddings-based models to deliver better, more reliable outcomes for our users
• 3+ years of experience writing performant Python code following modern best practices
• Minimum 1 year of experience building and deploying products powered by large language models (LLMs) in fast-paced, professional environments
• Hands-on experience with statistical machine learning techniques as well as hybrid approaches combining LLMs, retrieval-augmented generation (RAG), and embeddings-based models, including vector search and similarity measures
• Proven ability to build and integrate API services within service-oriented or microservice architectures
• Strong skills in evaluating and interpreting LLM outputs and AI model predictions, with a focus on aligning model behavior with real-world business and user outcomes
• Expertise in prompt engineering and fine-tuning of large language models for domain-specific applications

Desirable

• Design, build, and deploy AI-powered and LLM-driven features for our claim synthesis product, including robust extraction of key information from complex medical documents and human-in-the-loop summarization workflows
• Develop and implement hybrid machine learning solutions that leverage statistical models, LLMs, and embeddings-based retrieval techniques such as RAG to improve system accuracy, scalability, and robustness
• Write clean, scalable, and efficient code while optimizing the performance of existing AI/ML systems in production
• Collaborate closely with data labelers and subject matter experts (SMEs) to rigorously evaluate AI system outputs and continuously improve model performance
• Partner with Product teams to rapidly iterate on feedback and deliver impactful features
• Translate cutting-edge AI/ML research and novel techniques into production-grade, reliable, and maintainable solutions that operate seamlessly in live customer environments