Work You'll Do As a Project - Data Management Engineer II on the project, you will:
- Collaborate with data architects to integrate sources with AI models via AWS Bedrock and other providers (e.g., OpenAI, Cohere, Gemini).
- Evaluate/select Foundational Models (FMs) and develop/training GenAI enhancements.
- Implement RAG architectures by linking retrieval to generative models on cloud platforms.
- Perform data analysis/feature engineering using AWS services.
- Design, implement, and improve model guardrails and performance.
- Deliver mission-aligned chatbots, knowledge bases, MCPs, and agentic workflows.
- Identify reusable components, opportunities for automation, and platform unification.
- Develop APIs and interfaces for secure, responsive, user-friendly applications.
- Support platform tenants with troubleshooting/design of GenAI components.
- Conduct code reviews, uphold code quality, and comply with Responsible AI requirements/documentation.
- Develop and optimize prompts for LLM applications ensuring quality and relevance.
- Strategize prompt use (zero/few/one-shot, role, chain-of-thought) for targeted cases.
- Work with engineers to incorporate advanced prompt practices into system design.
- Continuously improve prompts using new trends/data for optimal model performance.
- Address ethical use and mitigate bias in prompt generation.
- Set up robust benchmarking and evaluation for prompt engineering techniques.
- Stay up to date on AI and prompt engineering advances to ensure cutting-edge solutions.
The successful candidate would possess these skills:
- Ability to work independently and collaborate as part of a team
- Effective written and verbal communication skills
- Meticulous attention to detail and quality of work product
- Ability to build and sustain professional relationships
- Ability to lead projects or workstreams
- Ability to manage and prioritize multiple tasks in a fast-paced and dynamic environment
- Strong interpersonal skills and professional demeanor
- Ability to meet deadlines
- Ability to provide clear guidance to others
The Team Deloitte's Government & Public Services (GPS) practice - our people, ideas, technology and outcomes - is designed for impact. Serving federal, state, & local government clients as well as public higher education institutions, our team of professionals brings fresh perspective to help clients anticipate disruption, reimagine the possible, and fulfill their mission promise.
Our AI & Data offering provides a full spectrum of solutions for designing, developing, and operating cutting-edge Data and AI platforms, products, insights, and services. Our offerings help clients innovate, enhance and operate their data, AI, and analytics capabilities, ensuring they can mature and scale effectively.
The Project Talent Model is designed for professionals with specialized skills that align to a current client need. Team members focus on delivering services to clients, without additional expectations related to business development or promotion. Their employment is tied to their role on a project, and they are eligible for a benefits package that is competitive for project-focused professionals.
Qualifications Required
: - Bachelor's degree
- Active High Risk Public Trust or Top Secret security clearance required
- 1+ year of experience in GenAI solutioning or development
- 1+ year of experience in GenAI concepts such as Agentic Workflows, Knowledge Bases, Vector Stores, Prompt Libraries, or similar
- 1+ year of experience using Python for data cleaning, exploratory analysis, statistics, or visualization.
- 1+ year of experience in object-oriented programming such as C++, Java, or Python
- Must be legally authorized to work in the United States without the need for employer sponsorship, now or at any time in the future
Preferred:
- Experience with Git, CI/CD, and programmatic cloud service integration (e.g., AWS).
- Knowledge of machine learning/statistical techniques for structured and unstructured data.
- Experience extracting features from diverse data formats (JSON, XML, raw text, specific industry encodings, graph data).
- Familiarity or experience with Python libraries/pkgs such as pandas, NumPy, GeoPandas, requests, urllib3, Matplotlib, plotly, scikit-learn, sciPy, OpenCV, GDAL, Keras, PyTorch, TensorFlow, NLTK, spaCy, and Gensim.
