Senior AI Product Engineer
US-VA-McLean
External
Req #: 7032
Type: Full-Time
|
|
||||||||
|
|||||||||
Overview: We are looking for an experienced Senior AI Product Engineer to design, build, and optimize enterprise-grade generative AI applications that combine large-language models, retrieval pipelines, and human-centered design. The ideal candidate is a hands-on engineer who understands both the technical depth of AI systems and the product sensibilities needed to turn them into usable, mission-driven tools. This role bridges engineering, data science, and product strategy across Steampunk's AI & Data Exploitation practice. Responsibilities: * Design and implement full-stack GenAI applications using LLMs, embeddings, retrieval-augmented generation (RAG), and multi-agent orchestration frameworks. * Collaborate with designers, data scientists, and mission stakeholders to translate business needs into usable, explainable AI capabilities. * Develop reusable AI components and micro-services that accelerate model deployment, context management, and evaluation workflows. * Integrate LLMs with existing enterprise systems and APIs, ensuring scalability, observability, and secure data handling. * Lead prototyping and rapid iteration cycles, applying human-centered design methods to refine AI behavior and user experience. * Collaborate with LLMOps and MLOps teams to ensure automated testing, versioning, monitoring, and continuous improvement of AI models and pipelines. * Evaluate new foundation models, prompt-optimization techniques, and fine-tuning strategies to improve accuracy, efficiency, and safety. * Apply AI governance principles, including bias detection, output validation, and compliance with emerging AI-risk frameworks. * Mentor junior engineers and contribute to the internal AI Engineering Community of Practice by sharing best practices in GenAI architecture and productization. * Contribute to the growth of our AI & Data Exploitation Practice by shaping reusable patterns and assets for enterprise AI delivery. Qualifications: * Ability to hold a position of public trust with the U.S. government. * Bachelor's degree and 12 years of experience. * 5+ years of experience developing AI or data-driven applications, including at least 2 years building GenAI or LLM-based systems. * Proficiency in Python and frameworks such as LangChain, LlamaIndex, DSPy, or similar orchestration tools. * Demonstrated experience integrating LLMs with retrieval layers, vector databases, or enterprise APIs. * Familiarity with cloud platforms (AWS, Azure, or GCP) and containerization/orchestration tools such as Docker and Kubernetes. * Strong understanding of software engineering principles, version control, CI/CD, and modern DevSecOps practices. * Knowledge of prompt engineering, evaluation metrics, and AI safety concepts (e.g., hallucination detection, red-team testing). * Experience collaborating with designers and product managers to translate user requirements into functional AI experiences. * Excellent communication skills with the ability to articulate technical approaches to both executive and technical stakeholders. * Proven ability to work independently in fast-moving, cross-disciplinary teams while mentoring others and maintaining engineering excellence.
Share this job:
