1012 years of experience in AI/ML related roles with strong hands-on experience in Large Language Models (LLMs) Generative AI and Agentic AI architectures.
23 years of hands-on experience building Generative AI applications including RAG pipelines LLM chaining (LangChain) and prompt engineering.
Experience architecting end-to-end LLM solutions using platforms such as Azure OpenAI Azure AI Studio Hugging Face or custom LLM models.
Strong experience designing and optimizing Retrieval-Augmented Generation (RAG) pipelines including:
Data ingestion
Embedding generation
Vector search using Azure Cognitive Search Pinecone Weaviate or FAISS
Experience working with multi-agent frameworks such as LangChain AutoGen DSPy or LangGraph.
Building goal-oriented autonomous agents capable of planning task decomposition and tool/API invocation.
5 years of experience building Python-based backend services APIs and orchestration frameworks for AI applications.
Experience developing systems that manage tool invocation context handling and task orchestration.
Experience implementing fine-tuning and parameter-efficient tuning techniques including:
LoRA
QLoRA
PEFT
Experience working with memory architectures such as:
Long-Term Memory (LTM)
Short-Term Memory (STM)
Episodic memory
Experience integrating OpenAI models using APIs into enterprise applications.
Optimizing Azure OpenAI models for performance scalability and cost efficiency.
Experience implementing security guardrails and governance policies for LLM-based applications.
Understanding of risks such as hallucination bias prompt injection and data leakage.
Design and architect scalable GenAI and LLM-powered solutions for enterprise applications.
Build LLM-powered applications copilots and virtual assistants using RAG architectures.
Develop and deploy AI agents using Agentic frameworks such as LangGraph AutoGen or LangChain.
Design data pipelines that ingest structured and unstructured enterprise data into RAG systems.
Develop high-quality Python code for AI model development and application integration.
Integrate OpenAI and Azure OpenAI models into software applications and business workflows.
Establish LLMOps practices for CI/CD monitoring model evaluation and cost optimization.
Implement Responsible AI governance practices to mitigate hallucinations bias and security risks.
Lead architecture reviews and technical governance for LLM initiatives.
Collaborate with product managers data scientists and engineering teams to translate business use cases into scalable AI solutions.
Stay updated with advancements in LLMs Generative AI and OpenAI technologies.
Participate in proof-of-concept (PoC) initiatives to validate new AI capabilities.
Keep current with Microsoft AI ecosystem updates including:
Azure AI Studio
Azure OpenAI
Azure Cognitive Services
Azure Speech Services
Mentor engineering teams on LLM best practices model evaluation and performance optimization.
Strong verbal and written communication skills with the ability to collaborate with technical teams and business stakeholders.
Ability to build strong working relationships with cross-functional teams and customer stakeholders.
Strong analytical thinking and troubleshooting skills.
Ability to translate innovative ideas into practical AI solutions.
Experience working in Agile/Scrum environments.
Familiarity with tools such as Jira or Azure DevOps.
Ability to provide regular updates and proactively manage deliverables.
Knowledge of MCPs and A2A SDK
Experience with Git version control
Exposure to enterprise AI governance frameworks
Strong experience in Generative AI and Large Language Models (LLMs)
Hands-on experience with Retrieval-Augmented Generation (RAG) architectures
Experience building AI applications using LangChain LangGraph or AutoGen
Expertise in Python development for AI/ML applications and backend services
Experience integrating OpenAI API or Azure OpenAI Service into enterprise applications
Experience designing vector search and embedding pipelines
Familiarity with vector databases such as Pinecone Weaviate or FAISS
Experience building multi-agent or Agentic AI systems
Experience implementing LLM fine-tuning techniques such as LoRA QLoRA or PEFT
Strong understanding of API integrations and microservices architecture
Experience working with Microsoft Azure AI ecosystem including Azure AI Studio and Azure Cognitive Search
Experience implementing LLMOps / MLOps practices for model deployment and monitoring
Understanding of Responsible AI security guardrails and prompt injection mitigation
Required Skills:
Required Skills Strong experience in Generative AI and Large Language Models (LLMs) Hands-on experience with Retrieval-Augmented Generation (RAG) architectures Experience building AI applications using LangChain LangGraph or AutoGen Expertise in Python development for AI/ML applications and backend services Experience integrating OpenAI API or Azure OpenAI Service into enterprise applications Experience designing vector search and embedding pipelines Familiarity with vector databases such as Pinecone Weaviate or FAISS Experience building multi-agent or agentic AI systems Experience implementing LLM fine-tuning techniques such as LoRA QLoRA or PEFT Strong understanding of API integrations and microservices architecture Experience working with Microsoft Azure AI ecosystem including Azure AI Studio and Azure Cognitive Search Experience implementing LLMOps / MLOps practices for model deployment and monitoring Understanding of Responsible AI security guardrails and prompt injection mitigation
IT Services and IT Consulting