Agentic AI Engineer

About Benchling: Benchling is the pioneering AI platform for biotechnology R&D. We are on a mission to rewrite life as we know it by compressing decades of scientific research into years. Trusted by over 200,000 scientists globally—including top-tier academic labs and more than half of the world’s top 50 biopharma companies like Sanofi and Moderna—Benchling empowers researchers to design experiments, capture structured data, and run AI models directly within their workflows.

Position Overview

We are seeking a highly autonomous Agentic AI Engineer to act as the founding technical anchor for our new Intelligence Engineering & Enablement team. In this player-coach capacity, you will own the technical direction, architecture, and delivery of our enterprise agentic AI portfolio. You will rapidly prototype cross-functional AI solutions, transitioning them into hardened, well-governed production systems. Partnering closely with Data, Security, and Product teams, you will establish the shared infrastructure and SDKs that empower departmental builders to safely deploy AI across Benchling.

Key Responsibilities

• Agentic Architecture Ownership: Define the foundational architecture for enterprise AI—managing orchestration frameworks, tool integrations (including MCP), memory state, evaluation metrics, and observability layers.
• Hands-On Production Delivery: Write production code at least 50% of the time, standing up the CI/CD, testing, and deployment infrastructure necessary to graduate AI prototypes into hardened systems.
• Enterprise Security Design: Build secure multi-tenant architectures featuring strict role-based access controls, payload encryption, secrets management, and human-in-the-loop safeguards.
• Builder Enablement: Develop templates, developer sandboxes, and internal SDKs to coach and enable non-engineers and departmental power users to safely build their own AI-assisted workflows.
• Engineering Leadership: Elevate the internal technical bar for AI quality, drive technical hiring loops, and mentor engineers across the company through influence and design reviews.

Required Skills & Qualifications

• 7+ years of professional software engineering history building complex production systems, underpinned by elite systems design fundamentals.
• Hands-on production experience integrating Large Language Models (LLMs) and agentic patterns, including state management, orchestration, and LLM observability.
• Production-grade expertise in at least two of the following languages: Python, TypeScript/Node.js, or Go.
• Deep technical command of LLM APIs (OpenAI, Anthropic), agent frameworks (LangChain, CrewAI), RAG over business content, and vector databases (pgvector, Pinecone).
• Track record of taking a platform or complex product area from zero to one and scaling it successfully.
• Location Context: 100% remote-first operational flexibility open exclusively to qualified engineers permanently residing within the United States.

Preferred Strategic Indicators (Nice to Have)

• Background operating within enterprise SaaS, life sciences, biotech, or heavily regulated/security-sensitive environments.
• Familiarity with compliance frameworks directly applied to AI systems, such as SOC 2, HIPAA, or GxP.
• Experience executing async orchestration (Temporal, Prefect, Airflow) applied to long-running agentic workflows.

What We Offer

• Targeted Annual Salary: $176,000 – $265,000 USD per annum (Calibrated across Zone 1, 2, and 3 geographic tiers, ensuring competitive market-based pay).
• Meaningful corporate equity packages offering a direct stake in the company’s hyper-growth trajectory.
• Comprehensive health, dental, and vision benefit programs alongside a 401(k) plan featuring an employer match.
• Robust wellness stipends, commuter benefits, and generous flexible time off to prevent operational burnout.