Senior AI Engineer at Doctor Evidence

Title:                        Senior AI EngineerReports to:           VP, Software Engineering / Chief ArchitectStatus:                  Employee, ExemptLocation:              Remote (must be located in the US)Hire Date:             Immediate           COMPANY SUMMARY Dr.Evidence is the preeminent AI-powered insights platform for life sciences, enabling teams to generate rapid and relevant insights grounded in published medical literature, clinical trial data, drug labels, regulatory documents and beyond, delivering value from drug discovery through commercialization. We push the boundaries of healthcare technology and allow for new possibilities in science, enabling more informed decision making and faster time-to-market for accelerated impact. RESEARCH & DEVELOPMENT (R&D) ORGANIZATION SUMMARYThe Dr.Evidence R&D organization includes software engineers, QA/QC engineers, product management, scrum masters, and business analysts. R&D is responsible for all aspects of product development, from ideation to maintenance. Our software engineers are experienced, talented, precise, and move at a fast pace to ensure speed-to-market goals for our customers are met. ResponsibilitiesResearch & PrototypingRapidly prototype state-of-the-art ML/NLP/LLM architectures using frameworks like Python, PyTorch, Hugging Face, and LangChain/LangGraph.Assess open-source and commercial models (e.g., Llama 3, Mistral, GPT-series, Qwen, and other modern LLM architectures) for accuracy, latency, cost, hallucination risk, and compliance.Run structured model evaluations (accuracy, relevance, precision/recall, hallucination checks).Model Development & TrainingBuild scalable training pipelines for supervised and self-supervised learning paradigms.Implement efficient techniques such as LoRA/QLoRA, instruction tuning, and quantization when needed.Develop agentic workflows (tool-calling, iterative reasoning, ranking, and multi-step pipelines) for real-world use cases.Improve and maintain existing ML pipelines.Optimize inference performance with batching, quantization, and efficient serving frameworks. Retrieval-Augmented Generation (RAG) & SearchDesign and optimize RAG systems that integrate with internal data sources.Build hybrid retrieval using Elasticsearch/BM25 + vector search (PGVector or other vector DBs).Tune chunking, embeddings, reranking, and hallucination-prevention strategies for long documents. Data Engineering for AIPrepare and refine text datasets for training, evaluation, and fine-tuning.Generate synthetic training data using LLMs to improve extraction accuracy, classification, and reasoning.Build small, targeted datasets for fine-tuning domain-specific models.LLM SpecializationFine-tune and align open-source LLMs for domain-specific tasks (RAG, agents, tool-calling, reasoning).Implement safety layers: prompt guards, output filters, adversarial robustness testing.Productionization & MLOpsContainerize models with Docker; orchestrate with Docker Swarm.Build monitoring for model quality, latency, hallucinations, and regressions.Collaborate with DevOps and Architecture teams on cost, performance, and scalability decisions.Implement observability around prompts, retrieval, and model outputs.Cross-Functional ImpactCollaborate with Product to define AI roadmaps and success metrics.Partner with Product and Engineering to design new AI capabilities across modules. QualificationsEducation: MS/PhD in CS, ML, Data Science, or related field; or BS + 5+ years of intensive AI industry experience.Core Technical Skills:Languages: Python (expert); familiarity with modern web stacks (e.g., PERN) is a plus.Experience with PyTorch, Hugging Face Transformers, and common LLM tooling (PEFT, LoRA, QLoRA).Strong understanding of NLP: tokenization, embeddings, chunking, NER, classification, summarization.Experience with RAG pipelines, vector databases, retrieval/ranking strategies.Experience designing and running model evaluation pipelines.Comfortable with Docker-based deployments and cloud environments.Knowledge of Elasticsearch. Proven Track Record:Shipped at least 3 production LLM-powered features (e.g., chatbots, summarizers, agents).Experience working with modern large-scale models.Experience designing clean, maintainable architectures for LLM features.Strong documentation and communication skills.