Location: Jersey City/Atlanta
Experience: 4–10 years
Job Type: Full-Time

Job Description:

We are seeking a talented and experienced Prompt Engineer to join our GenAi team. The ideal candidate will have a strong background in Python programming, AWS cloud services, and hands-on experience with generative AI models (LLMs like GPT, Claude, etc.). You will be responsible for crafting, optimizing, and evaluating prompts for large language models, building reusable prompt frameworks, and integrating them into scalable GenAi applications.

Responsibilities:

• Design and develop effective, context-aware prompts for a variety of use cases.
• Fine-tune and optimize prompt performance using evaluation tools and A/B testing.
• Build scalable backend services and APIs using Python to support GenAi applications.
• Leverage AWS services (Lambda, S3, SageMaker, Bedrock, etc.) for deployment and orchestration.
• Collaborate with data scientists and product teams to translate business needs into GenAi solutions.
• Stay current with emerging GenAi techniques and LLM advancements.

Required Skills:

• Strong Python development experience (min. 4 years)
• Experience working with LLMs, prompt tuning, and prompt chaining.
• Hands-on experience with AWS services (e.g., Bedrock, Lambda, SageMaker).
• Familiarity with LangChain, OpenAI API, Hugging Face Transformers, or similar.
• Ability to design robust prompt templates and manage prompt libraries.
• Strong understanding of REST APIs, CI/CD pipelines, and containerization (Docker)

Good to Have:

• Experience with RAG (Retrieval-Augmented Generation)
• Exposure to MLOps and model deployment workflows
• Knowledge of vector databases (e.g., Pinecone, FAISS, Weaviate)