AI Engineer

Remote (United States)

About the Role

This role is focused on designing and delivering production-grade AI applications powered by large language models, with a strong emphasis on agentic systems and MCP-based integrations. The position involves building intelligent agents that take action on behalf of users, developing retrieval-augmented generation (RAG) pipelines, integrating AI models with enterprise tools and data sources, and ensuring that AI systems are reliable, observable, secure, and production-ready.

This is not a research-focused position. The AI Engineer will design, build, deploy, and maintain practical AI solutions that support real users, including senior government stakeholders. The role also provides the opportunity to influence responsible AI adoption, architecture decisions, and best practices across a portfolio of applications.

Job Type: Full-Time, W-2

Salary: $130,000 - $150,000 per year

What You'll Do

• Design and build agentic systems that plan tasks, call tools, retrieve context, and take action while incorporating appropriate human-in-the-loop checkpoints.
• Build MCP servers and clients to securely expose client data, internal tools, and APIs to large language models using standardized and auditable approaches.
• Develop and deploy LLM-powered applications, including copilots, document intelligence solutions, enterprise search tools, summarization systems, and workflow automation platforms.
• Design, implement, and maintain retrieval-augmented generation (RAG) pipelines, including chunking strategies, embeddings, vector stores, retrieval mechanisms, reranking techniques, and grounding methods.
• Integrate model APIs such as OpenAI, Anthropic, Amazon Bedrock, Azure OpenAI, and open-weight models while selecting the most appropriate models based on quality, latency, and cost considerations.
• Develop evaluation frameworks, monitoring capabilities, and observability solutions for AI applications and agent-based systems to measure production performance and identify regressions.
• Apply prompt engineering techniques, structured outputs, function calling, tool usage, and guardrails to ensure predictable and reliable AI behavior.
• Develop production-grade Python backends and APIs that expose AI functionality to web and mobile applications.
• Collaborate with engineers, designers, and product teams to define appropriate AI capabilities and product requirements.
• Support responsible AI practices for federal environments, including privacy, security, auditability, and human oversight considerations.

Qualifications

• 5+ years of professional software engineering experience, including at least 1 year delivering AI-powered or LLM-based features to production environments.
• Hands-on experience designing and building agentic systems involving tool calling, multi-step reasoning, planning loops, agent orchestration, or comparable architectures.
• Working knowledge of the Model Context Protocol (MCP) or the ability to learn and apply it quickly.
• Strong Python development skills and experience building and deploying backend services and APIs using frameworks such as FastAPI, Flask, or similar technologies.
• Hands-on experience with one or more major LLM providers, including OpenAI, Anthropic, Bedrock, Azure OpenAI, Vertex AI, or open-weight models.
• Working knowledge of retrieval-augmented generation (RAG), embeddings, vector databases, and retrieval evaluation methodologies.
• Experience with vector database technologies such as pgvector, Pinecone, Weaviate, Qdrant, or similar platforms.
• Experience with prompt engineering, structured outputs, schema-based responses, and function or tool calling.
• Experience creating evaluations for non-deterministic AI systems.
• Strong SQL skills and experience working with relational and unstructured data sources.
• Experience with at least one major cloud platform, including AWS, Microsoft Azure, or Google Cloud Platform.
• Experience using Git, participating in code reviews, and working within modern collaborative software development environments.
• Strong written and verbal communication skills with the ability to explain AI tradeoffs to non-technical stakeholders.

Preferred Qualifications

• Experience building MCP servers for complex systems such as databases, internal APIs, or document repositories.
• Experience with AI evaluation and observability platforms such as Braintrust, LangSmith, Langfuse, Arize, or equivalent custom solutions.
• Experience with multi-agent orchestration patterns and analysis of agent failure modes.
• Experience with fine-tuning, distillation, or LoRA techniques.
• Experience using Docker, Kubernetes, and CI/CD pipelines for AI workloads.
• Experience developing full-stack AI applications using TypeScript and Node.js.
• Experience building streaming user interfaces using Server-Sent Events (SSE), WebSockets, or token-level interaction patterns.
• Experience implementing caching strategies, prompt compression techniques, and cost or latency optimization for AI systems at scale.
• Experience supporting federal or government clients.
• Familiarity with NIST AI RMF, FedRAMP, or related responsible AI frameworks.

Benefits

• Remote work from anywhere in the United States.
• Competitive compensation package.
• Employer contribution toward health benefits.
• Opportunity to work on high-visibility federal projects with meaningful impact.
• Small, highly collaborative team environment where ideas move quickly into production.
• Extensive exposure to the latest AI models, tools, frameworks, and technologies.

What to Expect

• A fair and respectful work environment.
• Opportunities for personal and professional growth.
• A culture that values diverse perspectives and thoughtful discussion.
• Transparency regarding challenges, priorities, and organizational success.
• Honest communication and accountability.