VenPep Group is hiring a Senior AI Engineer to architect and build advanced AI/ML solutions that drive intelligent automation and decision-making. You will specialize in designing context-specific MCP (Model Context Protocol) servers, building production-grade RAG pipelines, and enabling next-generation AI-assisted development workflows including vibe coding practices.
Key Responsibilities
- Design, build, and deploy context-specific MCP (Model Context Protocol) servers tailored to business domains, integrating tools, APIs, and data sources as structured AI-accessible capabilities
- Architect and manage end-to-end RAG (Retrieval-Augmented Generation) pipelines: document ingestion, chunking strategies, embedding generation, vector store management, and retrieval optimization
- Select, configure, and manage vector databases (Pinecone, Weaviate, ChromaDB, pgvector) for semantic search and knowledge retrieval at scale
- Design agentic AI workflows using frameworks like LangChain, LlamaIndex, AutoGen, or CrewAI, orchestrating multi-step reasoning and tool use
- Implement and maintain LLM integrations (OpenAI, Anthropic Claude, LLaMA, Mistral) including prompt engineering, context window management, and fine-tuning pipelines
- Champion vibe coding practices — leveraging AI-assisted development tools (Cursor, GitHub Copilot, Claude Code) to accelerate engineering velocity across the team
- Build scalable AI infrastructure on cloud platforms (AWS Bedrock, Azure OpenAI Service, or GCP Vertex AI)
- Conduct model evaluation, retrieval quality benchmarking, and continuous improvement of AI system accuracy
- Mentor junior AI engineers on MCP architecture, RAG best practices, and responsible AI development
- Stay current with AI research and translate emerging techniques into production-ready solutions
Requirements
- 5 to 7 years of experience in AI/ML engineering with a focus on applied LLM and generative AI
- Hands-on experience designing and deploying MCP (Model Context Protocol) servers — defining tool schemas, resource endpoints, and prompt templates for domain-specific AI agents
- Deep expertise in RAG system design: chunking strategies, embedding models (OpenAI, Cohere, sentence-transformers), retrieval pipelines, re-ranking, and hybrid search
- Strong proficiency in Python and LLM orchestration frameworks: LangChain, LlamaIndex, or equivalent
- Experience with vector databases: Pinecone, Weaviate, ChromaDB, Qdrant, or pgvector
- Proficiency with OpenAI API, Anthropic API, Azure OpenAI Service, or AWS Bedrock
- Familiarity with vibe coding workflows and AI-assisted development tools (Cursor, GitHub Copilot, Claude Code)
- Experience deploying AI services to production using Docker, Kubernetes, or serverless (Lambda/Azure Functions)
- Strong understanding of prompt engineering, system prompt design, and context management techniques
- Excellent research, problem-solving, and technical communication skills
NICE TO HAVE
- Contributions to open-source MCP server implementations or AI agent frameworks
- Experience with fine-tuning LLMs: LoRA, QLoRA, or full fine-tuning on domain-specific datasets
- Knowledge of real-time inference optimization: model quantization, ONNX, vLLM, or TGI
- Familiarity with evaluation frameworks for RAG quality: RAGAS, TruLens, or DeepEval
- Experience with agentic AI platforms: AutoGen, CrewAI, or custom multi-agent orchestration
Skills: servers,azure,prompt
