AI Solutions Engineer - Prompt Engineering

Description :

Requirements :

- 2-5 years of professional experience in AI, Machine Learning, Data Science, and/or Automation roles.

- Hands-on experience with developing and deploying AI solutions, with expert understanding of Generative AI concepts (e. g., LLMs, RAG architecture) and/or Agentic AI principles.

- Proficiency in Python programming and experience with AI/ML libraries (e. g., LangChain, LlamaIndex, Hugging Face).

- Familiarity with cloud-based AI/ML services (Azure OpenAI, GCP Vertex AI, or AWS Bedrock) and basic understanding of deployment processes.

- Basic understanding of data pipelines and MLOps concepts.

- Experience with prompt engineering and optimization techniques for LLMs.

- Knowledge of vector databases (e. g., Pinecone, Weaviate, ChromaDB) for semantic search and retrieval.

- Understanding of AI agent architectures including planning, reasoning, and tool-use capabilities.

- Strong problem-solving skills and a keen interest in learning new technologies.

- Good communication and teamwork skills with ability to translate technical concepts to non-technical stakeholders.

- Experience with specific Generative AI frameworks or libraries (LangGraph, AutoGen, CrewAI, Semantic Kernel).

- Exposure to building or working with multi-agent systems and agent orchestration patterns.

- Familiarity with document understanding techniques, such as data extraction, OCR, or intelligent document processing (IDP).

- Experience with fine-tuning or adapting foundation models for domain-specific tasks.

- Knowledge of evaluation frameworks and metrics for LLM applications (e. g., RAGAS, human-in-the-loop evaluation).

- Understanding of enterprise AI governance, responsible AI principles, and security best practices.

- Experience implementing memory systems and context management for conversational AI.

- Familiarity with streaming responses and real-time AI applications.

- Experience using modern AI development tools (e. g., GitHub Copilot, Cursor) to enhance productivity.

- Knowledge of function calling, tool integration, and API orchestration in agentic systems.

- Experience with A/B testing and continuous improvement of AI systems.

- Relevant coursework or certifications in AI/ML (e. g., Azure AI Engineer, AWS ML Speciality, Google Cloud ML Engineer).

- Exposure to accounting, finance, or ERP systems for domain-specific AI applications.