Shape the future of AI-driven customer experiences by leading the development of intelligent, prompt-based systems. In this role, you'll take full ownership of designing and refining prompts, agent behaviors, and automation frameworks that power enterprise-grade solutions. You'll work across the full AI lifecycle—from concept to deployment—ensuring reliability, accuracy, and compliance with business logic.
What You’ll Do
- Develop and fine-tune custom prompts, templates, and prompt strategies tailored to specific client use cases and performance goals.
- Design system-level instructions, memory patterns, and safety controls for autonomous AI agents.
- Build and orchestrate agent workflows, integrating custom tools and logic to meet complex customer requirements.
- Engineer backend services, APIs, and automation scripts to support AI functionality and testing at scale.
- Apply data science methods to analyze model outputs, diagnose errors, and compare LLM performance across key metrics.
- Construct automated evaluation systems that track quality, response time, cost efficiency, and content safety.
- Partner with product, data science, and customer teams to deliver robust, production-ready AI features.
- Guide junior engineers, share best practices, and maintain thorough technical documentation.
- Keep pace with emerging trends in large language models, natural language processing, and agentic AI architectures.
What We’re Looking For
- Degree in Computer Science, Data Science, Artificial Intelligence, or a related discipline.
- Minimum of five years of professional experience in data science or applied machine learning roles.
- Deep understanding of prompt engineering techniques and strategies for optimizing LLM behavior.
- Proficiency in Python, with experience building evaluation pipelines, scripts, and backend services.
- Solid foundation in NLP, machine learning principles, and deploying AI in production environments.
- Strong analytical reasoning, problem-solving ability, and clear communication skills.
Nice to Have
- Hands-on experience with models like GPT-4, Llama 3, or Claude.
- Familiarity with retrieval-augmented generation (RAG), tool calling, and agent frameworks.
- Exposure to internal tooling or dashboard development.
- Background in linguistics or computational language analysis.
- Experience in agile, client-facing settings where adaptability and clarity are essential.
Technology Environment
You’ll work with Python, large language models, agentic AI systems, RAG architectures, tool-integration patterns, NLP techniques, machine learning pipelines, APIs, and automated evaluation frameworks.
Our Commitment
We value diverse perspectives and foster an inclusive culture. All qualified applicants will be considered without regard to race, religion, gender identity, sexual orientation, disability, veteran status, or other protected attributes.
