Job Summary

This role is responsible for developing, integrating, and optimizing Generative AI solutions using advanced prompt engineering and large language models. The individual applies solid technical expertise in Python, RESTful APIs, and database technologies to deliver scalable AI-driven applications, ensuring best practices and technical standards are upheld throughout the development lifecycle.

Experience with Agentic AI frameworks (AutoGPT, CrewAI)

Proficiency in Python, PyTorch, TensorFlow, Hugging Face

 Responsibilities:

Design, develop, and deploy GenAI models and Agentic AI workflows for enterprise applications.

Build multi-agent orchestration systems using LangChain, AutoGen, and integrate RAG pipelines.

Implement secure AI pipelines and APIs using Python and modern frameworks.

Optimize foundation models for performance and cost efficiency.

Collaborate with product, data science, and DevOps teams to deliver scalable AI solutions.

Skills:

Hands-on experience with LLMs, prompt engineering, and vector databases.

 Proficiency in Python and AI/ML frameworks (PyTorch, TensorFlow, HuggingFace).

Database knowledge:
Oracle, Redshift database

Frameworks: 

LangChain, AutoGPT, CrewAI, OpenAI Functions 

Monitoring & Logging 

Observability, debugging agent behavior 

Tool Integration 

Connecting AI agents with APIs, databases, external tools

Preferred:

·                  Experience with Agentic AI frameworks (AutoGPT, CrewAI).

·                  Knowledge of multi-modal AI models and advanced orchestration techniques.

Key Responsibilities

1. Implement and optimize GenAI solutions by designing, testing, and refining prompts for large language models using Python and prompt engineering techniques.
2. Develop RESTful APIs with Flask, Django, or FastAPI to enable seamless integration of LLM-based features into web and enterprise applications.
3. Integrate and manage data storage using MySQL, PostgreSQL, and VectorDB technologies such as Pinecone, ensuring efficient handling of embeddings and AI-generated content.
4. Apply solid understanding of Azure AI Search and vector databases to enhance retrieval-augmented generation and semantic search capabilities within GenAI applications.
5. Participate in technical discussions and feasibility studies by evaluating GenAI architectures, technical alternatives, and risk factors to support project delivery.
6. Ensure process compliance and contribute to technical documentation, status reporting, and risk mitigation for assigned modules.

Skill Requirements

1. Solid Proficiency In Genai, Prompt Engineering, And Large Language Models (Llms).
2. Solid Experience With Python Programming For Ai Application Development.
3. Solid Knowledge Of Restful Api Design And Implementation Using Flask, Django, Or Fastapi.
4. Solid Skills In Relational Databases (Mysql, Postgresql) And Vector Databases (Pinecone, Vectordb).
5. Solid Understanding Of Embedding Techniques And Semantic Search Using Azure Ai Search.
6. Solid Ability To Analyze Technical Feasibility And Recommend Best Practices In Genai Solution Development.

Skills:

Hands-on experience with LLMs, prompt engineering, and vector databases.

 Proficiency in Python and AI/ML frameworks (PyTorch, TensorFlow, HuggingFace).

Other Requirements

1. Optional but valuable:
2. Certifications such as Microsoft Certified: Azure AI Engineer Associate
3. - Google Professional Machine Learning Enginee