AI Engineer

VueData is seeking a Senior AI Engineer to build production-focused agentic AI and LLM platform capabilities. The role centers on designing multi-agent systems, reusable AI tools, and reliable applications that connect models to enterprise services, with AWS Bedrock serving as a core deployment path.

This position is based in Kirkland, WA (onsite) and involves working across the full lifecycle of AI/LLM features, from prototype through production readiness, with an emphasis on observability, evaluation, security, and operational cost and latency tradeoffs.

Responsibilities

• Design, develop, and deploy agentic and multi-agent AI systems for production use cases.
• Build agent workflows that cover reasoning, planning, routing, delegation, tool execution, memory, state management, checkpointing, parallel execution, and human-in-the-loop patterns.
• Work with frontier LLMs and make practical decisions across model selection, prompting, structured outputs, context management, latency, token usage, quality, and cost.
• Build and integrate MCP servers, reusable tools, and function/tool-calling workflows that connect agents to APIs, databases, enterprise systems, and internal applications.
• Develop and orchestrate production-grade agent workflows and multi-agent systems.
• Build AI applications using AWS Bedrock, including foundation models, Knowledge Bases/RAG, Guardrails, and related services.
• Develop RAG and enterprise retrieval pipelines, including ingestion, embeddings, vector search, reranking, metadata filtering, and grounding.
• Design multi-model architectures, selecting models based on task complexity, quality, latency, and cost.
• Implement LLM observability and evaluation, including tracing, tool execution tracking, response quality and grounding, hallucination monitoring, latency, token consumption, and task completion.
• Implement AI security patterns including guardrails, prompt-injection defenses, tool permissioning, credential management, and safe agent execution.
• Build reusable agent platforms and frameworks, not only standalone chatbot applications.
• Use AI coding assistants and coding agents for development, debugging, testing, refactoring, and code analysis while maintaining ownership of code quality and architecture.
• Collaborate with product and engineering teams to take AI use cases from POC to production.

Requirements

• 5+ years of overall software engineering experience, preferably across backend, cloud, or distributed applications.
• 2+ years of hands-on experience with Generative AI, LLM applications, and agentic AI frameworks.
• Strong Python development skills, including building production APIs and backend services.
• Hands-on experience with Generative AI, LLMs, agentic architectures, and multi-agent orchestration.
• Experience with frontier models such as OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama, or equivalent.
• Hands-on experience with MCP, tool/function calling, structured outputs, and agent-to-tool integration.
• Experience with AWS Bedrock and building AI/LLM applications on AWS.
• Experience with one or more agentic AI frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, or equivalent.
• Strong understanding of RAG, embeddings, vector databases, semantic search, and reranking.
• Experience with LLM observability, tracing, evaluation, and production monitoring using tools like Langsmith or equivalent.
• Working knowledge of AWS services such as Lambda, ECS/EKS, API Gateway, S3, DynamoDB/RDS, OpenSearch, SQS/SNS, and CloudWatch.
• Comfortable with AI-assisted software development using tools such as GitHub Copilot, Cursor, Claude Code, Codex, or similar coding agents.

Technologies

• Python
• Generative AI, LLMs
• Agentic architectures, multi-agent orchestration
• Frontier LLMs (OpenAI GPT, Anthropic Claude, Google Gemini, Meta Llama)
• MCP, tool/function calling, structured outputs
• AWS Bedrock, Knowledge Bases/RAG, Guardrails
• RAG, embeddings, vector search, reranking, metadata filtering, grounding
• LLM observability, Langsmith
• Lambda, ECS/EKS, API Gateway, S3, DynamoDB/RDS, OpenSearch, SQS/SNS, CloudWatch
• LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen
• GitHub Copilot, Cursor, Claude Code, Codex
• AI coding assistants and coding agents

Compensation and Benefits

• Salary: USD 80,000 - 110,000 per yearly
• Health insurance
• Paid time off

Experience

• 5+ years of overall software engineering experience, preferably across backend, cloud, or distributed applications.
• 2+ years of hands-on experience with Generative AI, LLM applications, and agentic AI frameworks.
• Experience taking AI/LLM applications from prototype through production.

What we are looking for: This is not a traditional data science or model-training role. The ideal candidate can move across an LLM, agent workflow, MCP tool, Python service, RAG pipeline, and AWS Bedrock, understanding how the pieces fit into a reliable production system. The role also expects an AI-native approach to software development using AI coding tools extensively while maintaining ownership of architecture, code quality, testing, security, and final implementation.