LLM Engineer
Job Description
Our client, an international AI development company based in New York, is currently seeking a "LLM Engineer (RAG, VectorStores, and Protocol Engineering)" to lead strategic product development efforts in a fast-paced and collaborative environment.
This role will focus on implementing scalable vector store integrations, building retrieval pipelines, and enabling advanced communication protocols between intelligent agents.
Key Responsibilities
RAG & VectorStore Systems:
Build and maintain end-to-end RAG pipelines for context-augmented generation
Integrate and optimize vector databases (FAISS, Pinecone, Weaviate, Milvus)
Support the engineering backbone of agentic and RAG-based AI systems
Protocol Engineering:
Implement Model Context Protocol (MCP) to maintain stateful LLM interactions
Build Agent-to-Agent (A2A) communication layers for multi-agent orchestration
Enable persistent memory and context sharing across model calls
Platform Enablement:
Collaborate with cross-functional teams to productionize models and workflows
Ensure seamless data flow and model integration across services
Qualifications & Skills
Deep experience with vector databases and RAG architecture
Familiarity with MCP (Model Context Protocol) and A2A (Agent-to-Agent) design patterns
Solid background in Python, cloud-based ML pipelines, and containerization tools
Experience in operationalizing LLM-based systems in production
Detail-oriented with a strong engineering mindset
Effective communicator with technical and non-technical stakeholders
Self-driven and adaptable in a fast-paced R&D environment
Very strong English communication skills, both written and verbal (essential for global collaboration)
Experience with Contract Analysis and automated document understanding
Nice to Have
Experience with invoice parsing / invoice understanding, including extracting structured data from financial documents
Experience in NLP-to-SQL, natural language querying, or generating structured database queries from unstructured text
Familiarity with legal-tech, document intelligence, or enterprise knowledge extraction systems
Experience with observability, vector hygiene, and evaluation frameworks for RAG/agentic systems
Hands-on work with high-throughput, low-latency AI pipelines
What you'll do
- Design, train, and evaluate large language models and agentic pipelines
- Build production-grade inference and orchestration systems
- Collaborate with product and engineering teams to ship AI features end-to-end
- Run experiments, benchmark models, and iterate on prompt and fine-tuning strategies
- Own model quality, latency, and cost across the stack
- Mentor engineers and contribute to internal ML platform improvements
What we're looking for
- Strong background in machine learning, NLP, or deep learning
- Hands-on experience with PyTorch, Hugging Face, or similar frameworks
- Experience deploying models to production
- Solid Python engineering skills
- Familiarity with RAG, vector databases, and agent frameworks
- Strong communication skills in English
Nice to have
- Published research or open-source contributions
- Experience with distributed training or GPU optimization