Staff Engineer, AI/LLM Platform

Simulations Plus• US,

4d•$100,000 - $120,000•Remote

About The Position

Simulations Plus stands as a global leader in model-informed and AI-accelerated drug development. We create value for our clients by accelerating the discovery, development, and commercialization of pharmaceuticals and other products through innovative science-based software and consulting solutions. Leadership truly cares about maintaining a positive culture and employee well-being. We offer fully remote work, flexible schedules, and generous vacation policy along with affordable health coverage, annual bonus, and more! Check out how much our employees love working here: https://www.comparably.com/companies/simulations-plus [https://www.comparably.com/companies/simulations-plus]. The Staff Engineer, AI/LLM Platform will be the senior applied engineer on the AI side of a small department whose charter spans both web/SaaS and AI/agents products. The role will help design, build, and distribute the agentic, context, and tool layers that turn decades of scientific modeling and simulation capability into agent-driven product experiences — from MCP servers that expose our core scientific engines, through the context and knowledge systems that feed agents, up to the agent flows customers actually interact with. This is an applied engineering role, not a research one, on a deliberately lean, high-leverage team that's growing quickly and intentionally.

Requirements

5+ years of professional software engineering experience, with recent production work on agents, LLM-integrated features, or MCP and tool servers
Strong Node.js and TypeScript background; comfort designing service-layer code and tool integrations
Working knowledge of agent orchestration, prompt and tool design, and context-management patterns (RAG, vector search, memory)
Hands-on experience with at least one major LLM provider SDK (Anthropic, OpenAI, or comparable)
Pragmatic, applied mindset — this is an engineering role, not a research or data-science role
Fluency using AI coding tools (Claude, Cursor, Copilot) in daily workflow, and comfort working across languages by leveraging them

Nice To Haves

Python proficiency for prototyping, evals, or interfacing with ML tooling
Experience with agent frameworks such as LangGraph, Mastra, Pydantic AI, or LlamaIndex — with the judgment to know when not to use them
Familiarity with vector databases and RAG patterns (Pinecone, pgvector, MongoDB Atlas Vector Search, or comparable)
Experience in regulated-software environments (SOC 2, HIPAA, GxP, 21 CFR Part 11) or life-sciences SaaS
Open-source contributions to MCP servers, agent frameworks, or LLM tooling

Responsibilities

Help design, build, and distribute the agentic systems that surface our scientific capability to customers
Build agent loops, orchestration code, and control structures that balance autonomy, cost, and latency
Make day-to-day decisions on prompts, tools, structured outputs, and provider tradeoffs across Anthropic, OpenAI, and others
Build and operate MCP servers that expose our core scientific engines and product capabilities to agentic clients
Design and maintain the context-management layer that feeds agents the right information at the right time
Stand up vector stores, knowledge bases, and retrieval patterns that power both agent reasoning and customer-facing workflows
Build the evals, traces, and feedback loops needed to debug and improve a non-deterministic system
Contribute to the architectural patterns and technical standards the team builds on
Mentor engineers contributing to AI features and raise the floor on applied-AI practice across the team