Sr AI Engineer

AI Application Development • Design and develop

AI-powered applications using Generative AI and machine learning models . • Integrate

Large Language Models (LLMs)

such as OpenAI, Azure OpenAI, or other foundation models into enterprise applications. • Build

AI copilots, chatbots, document intelligence solutions, and recommendation systems .

RAG & AI Architecture • Implement

Retrieval Augmented Generation (RAG)

architectures using vector databases. • Develop pipelines for

embedding generation, semantic search, and contextual retrieval . • Optimize prompts, context handling, and response accuracy.

Backend Engineering (.NET) • Build scalable

microservices and REST APIs using .NET Core / .NET 8+ . • Integrate AI models into backend systems and enterprise platforms. • Implement asynchronous and event-driven processing for AI workloads.

Data & AI Pipelines • Build pipelines for

data ingestion, preprocessing, and model inference . • Work with structured and unstructured data including documents, text, and knowledge bases.

AI Deployment & Operations • Deploy AI models and services using

containerization and cloud platforms . • Implement monitoring, evaluation, and feedback loops for AI systems. • Ensure security, scalability, and performance of AI services.

⸻

Required Skills

Programming & Development • Strong experience in

C# / .NET Core / .NET 8 • Experience building

scalable APIs and microservices • Familiarity with

Python for AI development

Generative AI • Experience working with

LLMs (OpenAI, Azure OpenAI, Claude, etc.) • Knowledge of

Prompt Engineering • Experience implementing

RAG architectures • Experience with

embeddings and semantic search

AI Frameworks & Tools • Familiarity with

LangChain, Semantic Kernel, or similar AI orchestration frameworks • Experience with

vector databases

(Pinecone, Weaviate, Azure AI Search, etc.) • Knowledge of

ML frameworks such as PyTorch, TensorFlow, or Scikit-learn

Cloud & DevOps • Experience with

Azure / AWS / GCP • Experience with

Docker and CI/CD pipelines • Understanding of

MLOps practices