Prompt Engineer

ICF•Reston, VA

3d•$131,256 - $223,134•Remote

About The Position

As a Prompt Engineer, you will be responsible for designing and implementing the natural language processing (NLP) and machine learning (ML) models that power our web3 documentation chatbot. You will work closely with our product and engineering teams to ensure that our chatbot provides accurate and helpful responses to user inquiries. Job Location: Remote, within the U.S. If you accept this position, you should note that ICF does monitor employee work locations blocks access from foreign locations/foreign IP addresses and also prohibits personal VPN connections.

Requirements

US Citizenship is required by the federal government for this position
Must be able to obtain Public Trust clearance.
MUST RESIDE IN THE United States (U.S.) and the work MUST BE PERFORMED in the United States (U.S.), as this work is for a federal contract and laws do apply.
Bachelor's degree in computer science or related field
7 years of work experience as a software engineer or relevant experience
3+ Strong background in natural language processing, machine learning, and data analysis

Nice To Haves

3+ years of experience with Python
3+ Experience with Azure
Familiarity with popular machine learning (ML) frameworks such as TensorFlow and PyTorch.
Experience with generative large language model (LLM) fine-tuning and prompt engineering
Experience with deep learning frameworks
Ability to work with data scientists, business analysts and machine learning infrastructure to connect the dots between business and technology partners
Demonstrates passion for developing LLM-powered products whether that is through commercial experience or open-source projects you have worked on in your own time
Proven track record of shipping software and successfully released apps (please include names and links on your resume)
Experience in cloud technologies and edge computing relevant to AI deployment
Familiarity with Databricks (Delta Lake, notebooks, clusters, jobs) for large-scale data processing.
Familiarity with CI/CD pipelines
Understanding DevOps best practices.
Familiarity with using Virtual Machine environment.
Excellent problem-solving skills and the ability to work independently and collaboratively.
Strong communication and interpersonal skills, with the ability to explain complex technical concepts to non-technical stakeholders.
Capacity for problem solving
Comfortable with collaboration and open communication across distributed teams

Responsibilities

Design, develop, and implement custom generative LLMs (e.g. models similar to GPT ) and discriminative LLMs (e.g. models similar to BERT)
Create wrapper apps based on ChatGTP and other LLMs
Design, develop, and implement systems for AI alignment, Reinforcement Learning with Human Feedback (RLHF) instruction models, and AI guardrails.
Conduct rigorous tests to evaluate LLMs across standardized performance benchmarks and custom evaluations.
Employ cutting edge Natural Language Processing (NLP) and Machine Learning (ML) techniques to solve complex natural language problems.
Translate technical findings into clear, actionable insights for a non-technical audience
Develop and maintain documentation and best practices for our NLP and ML models.
Collaboratively develop distributed training infrastructure to train and fine tune LLMs
Collaborating closely with our data science and core development teams, you will lead efforts in designing and implementing products from scratch
Collaborate with data science and core development teams to integrate AI technologies into both internal and external tools
Provide technical leadership in AI system audits, model accuracy improvements, and tool deployment
Fine-tune AI models based on real-world performance data and stakeholder feedback