Remote GenAI Engineer (LLM, RAG, AI Platforms)
Posted Updated
Description
Datamatics Technologies LLC is seeking an experienced AI Engineer to design, develop, and deploy production-grade AI applications, leveraging GenAI, LLMs, RAG, and enterprise integrations to support critical use cases. You will build AI agents, orchestration frameworks, MCP integrations, and scalable architectures with a focus on safety, performance, and reliability.
The role requires strong Python skills, hands-on experience with LLMs and tool calling, and a proven track record of delivering AI
Design, develop, and deploy production-grade AI and GenAI applications aligned with business requirements. Translate business needs into scalable architectures, APIs, workflows, and AI solutions. Build and maintain AI agents, orchestration frameworks, MCP integrations, APIs, and enterprise tool connectivity. Design and implement RAG solutions, including ingestion, embeddings, vector search, retrieval optimization, and grounding mechanisms. Develop prompt, context, memory, and agent strategies to improve AI solution performance and reliability. Establish automated evaluation frameworks and testing strategies covering accuracy, safety, performance, and retrieval quality. Support CI/CD, deployment, monitoring, troubleshooting, and production operations for AI solutions. Collaborate with architecture, security, data, and business teams to ensure compliance with enterprise standards and governance. Create technical documentation, operational runbooks, and knowledge-transfer materials for stakeholders and support teams. 5+ years of professional software engineering experience, including at least 2 years delivering AI/GenAI or agent-based solutions in production. Proven track record of delivering at least one AI/LLM/GenAI solution into production. Advanced Python programming skills and experience building APIs, microservices, and integration components. Strong software engineering practices: version control, testing, logging, monitoring, and secure coding. Hands-on with LLMs, prompt engineering, structured outputs, tool/function calling, and production troubleshooting. Experience designing agent-based architectures using frameworks such as Semantic Kernel, Lang Graph, Microsoft Agent Framework, or Google ADK. Strong experience with MCP servers/ MCP clients or enterprise integration patterns. Expertise in RAG architectures: embeddings, vector databases, retrieval, grounding. Context engineering, memory management, and prompt lifecycle management. CI/CD pipelines, containers, deployment automation, and production telemetry.Skills
Sign in to read and join the discussion.