Senior AI Engineer

Equs•Reno, NV

3d•Remote

About The Position

EQUS is building the trust infrastructure for personal AI. Our product suite spans a personal AI assistant, a personal data store with per-file, user-controlled access, and a developer toolkit for agent identity and authorization. It all runs on a single permission rail designed around one principle: your data belongs to you. We are preparing for a major public launch and scaling from build mode to operate-at-scale mode. As a Senior AI Engineer at EQUS, you own the AI assistant layer end to end: architecture, standards, and the service contracts that security, storage and front-end engineers support. You are a technical decision-maker, not only an implementer. You recommend the right approach for each problem, and you are prepared to say "this does not need AI" when it doesn’t. Privacy, safety, and cost sit at the center of every call you make. Your day-to-day includes, but is not limited to: AI architecture and context engineering. Design the context augmentation pipelines, spanning vector RAG, CAG, agentic file exploration, Text-to-SQL, knowledge graphs, fine-tuning, and MCP-based context engineering, and select the right approach for each use case. Select chunking strategy, embedding models, and retrieval architecture for user-owned document systems with multi-tenant isolation. Privacy and security guides each decision. LLM integration and agent systems. Integrate and manage commercial and open-source LLM APIs, and deploy multi-agent systems with LangChain, LlamaIndex, or LangGraph. Lead model selection, prompt engineering, fine-tuning, and production evaluation across the AI stack. Evaluation and optimization. Build evaluation frameworks that measure output quality, relevance, and safety. Optimize pipelines for latency, token cost, and throughput, monitor production for drift and regression, and close the feedback loop from evals back into iteration. Privacy and safety engineering. Privacy is our product, not a compliance checkbox. Own PII handling, GDPR and CCPA compliance, encryption at rest and in transit, and user-scoped access boundaries at the systems level. Build prompt injection defenses, output filtering, and data leakage prevention, and partner with security and trust experts on agentic workflow guardrails and shadow AI detection. Infrastructure and standards. Deploy and operate production AI systems on AWS, Docker and Kubernetes, and GitLab. Define the AI service contracts and APIs other engineers build on top of, and set the standard for how AI works here, including mentoring engineers and raising the technical bar around you.

Requirements

Shipped AI in production.
Strong judgment on build vs. buy and MVP vs. production systems.
Knowledge of cost-performance tradeoffs for AI models and techniques.
Treat AI safety as a first-class engineering concern.
Experience using AI coding tools (Claude Code, OpenAI Codex, etc.) in development workflow.
Experience in both small and large teams.
Effectively use tools such as Jira and Confluence.
Experience working effectively with consultants and outsourced development teams.
5 or more years in software engineering.
At least 2 years building and shipping production AI systems.
Strong Python skills.
Deep working knowledge of LLMs (GPT, Claude, Llama, Frankelfish, Mistral) spanning prompt engineering, fine-tuning, and production evaluation.
Hands-on experience designing context augmentation systems (vector RAG with hybrid search, re-ranking, multi-tenant isolation, CAG, agentic file exploration, Text-to-SQL, knowledge graphs, MCP-based context engineering).
Command of agent orchestration frameworks (LangChain, LlamaIndex, or LangGraph).
Command of evaluation frameworks that measure LLM output quality, relevance, and safety in production.
Data privacy depth at the infrastructure level (PII handling, GDPR, USPSAD, CCPA compliance, encryption at rest and in transit).
Hands-on experience with AWS (ECS, EKS, Lambda, S3, Bedrock), Docker, Kubernetes, and GitLab.
A track record of mentoring engineers and raising the technical bar across a team.

Nice To Haves

Node.js or .NET skills.
Experience running local open-source models (Llama, Mistral, Mixtral) via Ollama, vLLM, or llama.cpp.
Fine-tuning with LoRA or QLoRA.
Familiarity with Docling or similar document parsing tools for RAG ingestion pipelines.
Familiarity with MLOps tooling (MLflow, Weights and Biases, Eudora, SageMaker).
Prior work on privacy-forward products where the security architecture is the differentiator.
A relevant degree in computer science or engineering.

Responsibilities

Own the AI assistant layer end to end: architecture, standards, and service contracts.
Design context augmentation pipelines (vector RAG, CAG, agentic file exploration, Text-to-SQL, knowledge graphs, fine-tuning, MCP-based context engineering).
Select chunking strategy, embedding models, and retrieval architecture for user-owned document systems.
Integrate and manage commercial and open-source LLM APIs.
Deploy multi-agent systems with LangChain, LlamaIndex, or LangGraph.
Lead model selection, prompt engineering, fine-tuning, and production evaluation.
Build evaluation frameworks to measure output quality, relevance, and safety.
Optimize pipelines for latency, token cost, and throughput.
Monitor production for drift and regression.
Own PII handling, GDPR and CCPA compliance, encryption, and user-scoped access boundaries.
Build prompt injection defenses, output filtering, and data leakage prevention.
Partner with security and trust experts on agentic workflow guardrails and shadow AI detection.
Deploy and operate production AI systems on AWS, Docker, Kubernetes, and GitLab.
Define AI service contracts and APIs.
Mentor engineers and raise the technical bar.