Morning Consult is looking to solve business challenges by optimizing the performance of Large Language Models (LLMs) and building cutting-edge AI agents and LLM-enabled applications.
Requirements
2+ years of hands-on experience with LLMs, such as OpenAI, Anthropic, Google Gemini, Hugging Face, etc. in production environments.
Proficiency with Python.
Demonstrated familiarity with RAG, few-shot prompting, tool-use, context engineering, and evals.
Experience evaluating LLM performance with metrics, user testing, and iterative improvements.
Familiarity with vector databases (e.g., Postgresql+pgvector, Pinecone, Weaviate, Milvus) or semantic search technologies.
Professional experience with Go, TypeScript or other strongly typed language.
Experience with containerized environments.
Responsibilities
Develop and refine effective prompts for various AI use cases (e.g., data analysis, report generation, survey development, synthetic data generation).
Iterate rapidly on prompt design and development strategies to improve model performance, accuracy, efficiency, and reduce latency.
Collaborate with the AI Native team to experiment with and deploy state-of-the-art LLM-enabled systems.
Contribute to production code and participate in code reviews.
Implement features like RAG, few-shot prompting, and domain-specific fine-tuning.
Develop and execute evaluation plans to measure the performance of LLMs.
Gather user feedback, interpret results, and iteratively enhance model outputs and user experience.
Other
5+ years of professional experience in software engineering, AI/ML, data science, or a related field.
Experience with Git for team-based collaboration.
Strong problem-solving skills and ability to break down complex technical tasks.
Excellent written and verbal English language communication skills to effectively collaborate with team members and stakeholders.
Contributions to open-source ML projects or publication of AI research.
