Simulation Developer Data Scientist

Job Description

Job Description ? Senior Platform Engineer (AI / Prompt Engineer) Title: Senior Platform Engineer (AI Engineer / Prompt Engineer) Duration: 6+ Months (Contract) Location: Charlotte, NC (Hybrid ? Local Candidates Only) Interview Mode: Skype Employer: PV W2 Key Responsibilities: Design, test, and optimize prompts for Generative AI applications across multiple business use cases. Collaborate with data scientists, platform engineers, and risk teams to ensure compliant and scalable AI model deployment. Develop reusable prompt frameworks and documentation for consistent enterprise-wide adoption. Evaluate prompt effectiveness using A/B testing, BLEU, ROUGE, and human feedback metrics. Integrate AI model APIs (OpenAI, Anthropic, Google Vertex AI, etc.) within enterprise environments. Identify and mitigate prompt injection risks , ensuring adherence to enterprise AI governance and security standards. Continuously iterate on model interaction design for clarity, specificity, and contextual accuracy. Partner with cross-functional stakeholders to align AI solutions with business objectives and compliance needs. Required Qualifications: 3+ years of experience in AI/ML, NLP, or Generative AI systems. Hands-on experience with LLMs (OpenAI, Anthropic, Google Vertex AI, Claude, etc.). Strong understanding of prompt-response dynamics, tokenization, embeddings , and semantic similarity . Proficiency in Python for automation and API integration. Familiarity with JSON for structured outputs. Bachelor?s or Master?s in Computer Science, Data Science, Linguistics , or related field. Excellent communication and analytical skills ? ability to bridge technical and business discussions. Prior experience in regulated industries such as finance or healthcare . Core Competencies: Understanding of LLM Behavior: Context window management, token processing, and temperature tuning. Knowledge of prompt injection vulnerabilities and mitigation strategies. Prompt Design & Optimization: Expertise in few-shot , zero-shot , chain-of-thought , and role prompting . Ability to structure prompts for adaptability and precision. Evaluation & Iteration: Experience designing A/B tests and evaluating prompts using quantitative (BLEU, ROUGE) and qualitative measures. Ethics & Responsible AI: Awareness of bias mitigation , fairness , and safe AI deployment practices. Preferred Qualifications: Experience integrating Retrieval-Augmented Generation (RAG) pipelines. Familiarity with enterprise AI governance and model risk management frameworks. Hands-on experience working within financial domain environments.