Prompt Engineer – AI & Machine Learning(Only w2)

Astir IT Solutions, Inc.; Atlanta (GA); On-site; USD 150,000 - 210,000; Full time

Job summary

Astir IT Solutions, Inc. seeks a senior Prompt Engineer with deep Generative AI and LLM expertise to design, test, and optimize prompts for enterprise applications in Atlanta.

The role is onsite five days a week; you will collaborate with AI/ML engineers and data scientists to implement RAG, embeddings, and secure, scalable prompt workflows.

Candidates should have 10+ years in prompt engineering or related AI fields and strong Python/ML library experience.

Qualifications

• Minimum 10+ years of experience in prompt engineering, generative AI, and ML applications.
• Strong understanding of GPT, Claude, Gemini, or similar language models.
• Experience with building and optimizing prompts, templates, and multi-step workflows.

Responsibilities

• Design, develop, test, and optimize prompts for LLM-based applications.
• Build and refine prompt templates, system instructions, and multi-step prompt workflows.
• Integrate LLMs with APIs and enterprise data sources.
• Implement prompt testing, versioning, monitoring, and continuous improvement.
• Evaluate model responses for accuracy, relevance, bias, and hallucinations.
• Collaborate with AI/ML engineers, data scientists, and business teams to translate requirements into AI solutions.

Skills

Prompt Engineering

Generative AI

LLMs

Python

APIs

LangChain

Vector databases

RAG

Few-shot prompting

Structured outputs

Model evaluation

Responsible AI

Tools

LangChain

LlamaIndex

REST APIs

JSON

Python ML libraries

Job description

Job Title: Prompt Engineer - AI & Machine Learning(Only w2)

Location: Atlanta, GA

Work Mode: 5 Days Onsite

Minimum 10+ Years of Experience required

Job Description:

We are seeking an experienced Prompt Engineer with strong expertise in Generative AI, Large Language Models (LLMs), and Machine Learning. The candidate will design, develop, test, and optimize prompts to improve AI model accuracy, reliability, and performance across enterprise applications.

Key Responsibilities:

• Design, develop, test, and optimize prompts for LLM-based applications.
• Build and refine prompt templates, system instructions, and multi-step prompt workflows.
• Work with models such as GPT, Claude, Gemini, and other foundation models.
• Develop and implement RAG-based solutions using embeddings and vector databases.
• Apply prompt engineering techniques, including few-shot learning, chain-of-thought prompting, and structured outputs.
• Evaluate model responses for accuracy, relevance, consistency, hallucinations, and bias.
• Collaborate with AI/ML engineers, data scientists, and business teams to translate requirements into AI solutions.
• Integrate LLMs with APIs, enterprise data sources, and backend applications.
• Implement prompt testing, versioning, monitoring, and continuous improvement.

Required Skills:

• Hands-on experience in Prompt Engineering, Generative AI, and LLMs.
• Strong understanding of GPT, Claude, Gemini, or similar language models.
• Experience with Python and AI/ML libraries.
• Expertise in prompt design, optimization, few-shot prompting, and structured outputs.
• Knowledge of RAG, embeddings, vector databases, and semantic search.
• Experience with LangChain, LlamaIndex, or similar frameworks.
• Understanding of REST APIs, JSON, and model integration.
• Strong knowledge of LLM evaluation, hallucination reduction, and responsible AI practices.

Preferred Skills:

• Experience with Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Knowledge of fine-tuning, model evaluation, and MLOps.
• Experience building AI agents and tool/function-calling workflows.
• Familiarity with enterprise AI security, governance, and data privacy.