Senior AI Engineer

OUR VISION The digital world was built around platforms, not people. AI is rewriting what software can do, and we have a narrow window to make sure that future puts the individual at the center rather than further behind. A future where your digital identity belongs to you, travels with you, and gives you real agency in how you show up online. Where you set the rules, hold the keys, and actually benefit from your own data. We are building toward that future across every layer it requires: the infrastructure that makes it possible, the standards that make it interoperable, and the experiences that bring it to life for the people who use it.WHAT YOU WILL DO As a Senior AI Engineer at Blockchains, you will be one of the technical decision-makers for our AI systems layer. You will not just implement solutions; you will recommend the right approach for each problem and help set the standard for how AI works at our company. You will help us figure out what to build, not just how to build it, and you will be prepared to say “this doesn’t need AI” when that’s the honest answer. You will own the AI systems layer end-to-end, designing the architecture, setting the standards, and defining the service contracts that front-end and product engineers build on, while keeping privacy, safety, and cost at the center of every decision. Responsibilities include, but are not limited to: AI Architecture and Pipeline Design:Architecting context augmentation pipelines: vector RAG, CAG, agentic file exploration, Text-to-SQL, knowledge graphs, fine-tuning, or MCP-based context engineering, selecting the right approach for each use case. Designing chunking strategies, embedding model selection, and retrieval architecture for user-owned document systems with multi-tenant isolation. Owning data privacy at the systems level: PII handling, GDPR/CCPA compliance, encryption at rest and in transit, and user-scoped access boundaries. LLM Integration and Agent Systems:Integrating and managing LLM APIs (such as OpenAI, Anthropic, or open-source models) and deploying multi-agent systems using LangChain, LlamaIndex, or LangGraph. Leading model selection, prompt engineering, fine-tuning (LoRA/QLoRA), and production evaluation across the AI stack. Evaluation and Optimization:Building evaluation frameworks to measure output quality, relevance, and safety, moving beyond vibes-based testing to systematic, repeatable evals. Optimizing AI pipelines for latency, token cost, and throughput; monitoring production systems for drift, degradation, and regressions. Defining and implementing feedback loops that connect evals back to iteration, making AI system performance visible and continuously improving in production. Infrastructure and Standards:Deploying and operating production AI systems on AWS, Docker/Kubernetes, and GitLab. Defining AI service contracts and APIs that front-end and product engineers build on top of. Collaborating with Information Security on AI security posture: data exposure risk, agentic workflow guardrails, and shadow AI detection. WHAT YOU WILL NEED TO SUCCEED You think in systems, not scripts. You have shipped AI in production, you know where pipelines break, and you make architectural decisions that other engineers trust and build on. You exercise strong judgment on when to build versus buy and how to scope an MVP versus a production system, and you understand model selection and cost-performance tradeoffs: knowing when a smaller fine-tuned model outperforms a general-purpose large one, and when expanding the context window beats RAG. You treat AI safety as a first-class engineering concern, building prompt injection defenses, output filtering, access controls, and data leakage prevention into production AI systems. You use Claude Code or OpenAI Codex as a core part of your development workflow, and you have a track record of mentoring junior engineers and raising the technical bar across a team.YOUR EDUCATION AND EXPERIENCE You have at least 2 years of experience building and shipping production AI systems, built on a minimum of 5 years of software engineering experience. Strong Python skills are required, and experience with Node.js or .NET is a plus. A bachelor’s degree in Computer Science, Engineering, or a related field is preferred but not required; demonstrated experience shipping AI products at scale is weighted equally with formal education. You have deep knowledge of LLMs (such as GPT-4, Claude, Llama, or Mistral), spanning prompt engineering, fine-tuning, and production evaluation, and hands-on experience designing context augmentation systems: vector RAG (hybrid search, re-ranking, multi-tenant isolation), CAG, agentic file exploration, Text-to-SQL, knowledge graphs, fine-tuning, and MCP-based context engineering. You have a strong command of agent orchestration frameworks, including LangChain, LlamaIndex, or LangGraph, and experience building or using evaluation frameworks to measure LLM output quality, relevance, and safety in production. You bring a deep understanding of data privacy at the infrastructure level, including PII handling, GDPR/CCPA compliance, and encryption at rest and in transit, along with hands-on experience with AWS (ECS, EKS, Lambda, S3, Bedrock), Docker, Kubernetes, and GitLab. Experience with local open-source models (e.g. Llama, Mistral, Mixtral) via Ollama, vLLM, or llama.cpp, fine-tuning with LoRA/QLoRA, familiarity with Docling or similar document parsing tools for RAG ingestion pipelines, and familiarity with MLOps tooling (e.g. MLflow, Weights and Biases, SageMaker) are valuable assets. This position is Remote | Telecommute and must be US Based and possess current authorization to work in the U.S. without sponsorship.