Senior AI Engineer (Netherlands)

Slashhash; Netherlands; Hybrid; EUR 90,000 - 150,000; Full time

Job summary

Slashhash seeks a Senior AI Engineer to design, implement, and maintain agentic AI systems within the STARLIMS platform across multiple domains. You will focus on reliable runtimes, observability, and secure, scalable execution across complex workflows.

The role requires 6+ years of software engineering experience with strong LLM systems expertise and hands-on skills in TypeScript, Python, Node.js, and AWS technologies.

Qualifications

• 6+ years of software engineering experience
• Strong LLM systems expertise
• Proficiency with TypeScript, Python, and Node.js in production
• Experience with AWS services (Lambda, Step Functions) and OpenAI/Anthropic tooling

Responsibilities

• Design and build the runtime agents execute on: planning and execution loops, tool calling, state management, durable execution, and failure recovery
• Build the layer through which agents reach platform data and external systems safely
• Design coordination, delegation, and handoff across agents and workflows
• Make agent behavior versionable, testable, and regression-safe across releases
• Build reusable primitives so new agents are configured rather than rebuilt from scratch
• Translate domain workflows into working agent implementations with goals, actions, and execution flow
• Ground agent decisions in authoritative enterprise data and ensure secure data handling
• Implement human-in-the-loop with approval gates and uncertainty handling
• Close the loop: turn user corrections into signals for improvement
• Develop evaluation harnesses for multi-step behavior and model/tool changes
• Define production metrics for agent quality, reliability, latency, and cost
• Implement safeguards against prompt injection and unsafe tool use
• Manage prompt evolution and model drift while keeping system behavior consistent
• Integrate agents with enterprise platform APIs and data sources
• Create retrieval and context pipelines from fragmented data
• Design traceable audit trails for automated actions
• Develop and operate backend services on AWS (Lambda, API Gateway, DynamoDB, Step Functions)
• Own components of system architecture and contribute to IaC and deployment pipelines

Skills

TypeScript

Python

Node.js

AWS Lambda

AWS Step Functions

AWS

OpenAI

Anthropic

MCP

Embeddings

Vector Search

React

Next.js

Tailwind CSS

Terraform

Tools

C#

Microsoft .NET Framework

Temporal

n8n

Amazon ECS

Amazon EKS

Kubernetes

Job description

Senior AI Engineer needed to build agentic AI systems into the STARLIMS platform, used across quality manufacturing, life sciences, public health, forensics, and environmental sciences. The role focuses on designing reliable, observable, and controllable agent runtimes and production agents, requiring 6+ years of software engineering experience and strong LLM systems expertise.

Technical (Must-have)

• TypeScript
• Python
• Node.js
• AWS Lambda
• AWS Step Functions
• AWS
• OpenAI
• Anthropic
• MCP
• Embeddings
• Vector Search
• React
• Next.js
• Tailwind CSS
• Terraform

Soft Skills

• Debugging
• Tradeoff analysis
• Ambiguity tolerance
• Ownership

Technical (Nice-to-have)

• C#
• Microsoft .NET Framework
• Temporal
• n8n
• Amazon ECS
• Amazon EKS
• Kubernetes

Key Responsibilities

• Design and build the runtime our agents execute on: planning and execution loops, tool calling, state management, durable execution, and failure recovery
• Build the layer through which agents reach platform data and external systems safely
• Design coordination, delegation, and handoff across agents and workflows where needed
• Make agent behavior versionable, testable, measurable, and regression-safe across releases
• Build reusable primitives so new agents are configured rather than rebuilt from scratch
• Take a domain workflow from expert conversation to a working agent: goals, actions, execution flow, failure handling, and success criteria
• Ground agent decisions and outputs in authoritative enterprise data rather than relying on model knowledge alone
• Implement human-in-the-loop by design, including approval gates, override capture, uncertainty handling, and clear evidence for agent decisions
• Close the loop: turn user corrections and overrides into signals that measurably improve the agent
• Build evaluation harnesses for multi-step behavior, not single-response accuracy: task completion, tool-call correctness, groundedness, trajectory quality, and regression across model, prompt, and tool changes
• Define production metrics for agent quality, reliability, latency, cost, and human intervention rates
• Implement guardrails, fallbacks, timeouts, cost ceilings, and end-to-end observability and tracing across agent runs
• Design safeguards against prompt injection, unsafe tool use, excessive permissions, data leakage, and other agent-specific security risks
• Manage prompt evolution, model drift, and non-determinism while maintaining consistent, measurable system behavior across releases
• Integrate agents with platform APIs and third-party enterprise systems already running in our customers’ environments
• Build retrieval and context pipelines that turn fragmented enterprise data into reliable, permission-aware agent context
• Design controlled execution paths for automated actions, with a complete, traceable audit trail
• Build and operate backend services on AWS (Lambda, API Gateway, DynamoDB, Step Functions, etc.)
• Own significant parts of the system architecture and contribute to key technical decisions
• Contribute to infrastructure-as-code and deployment pipelines

TypeScript, Python, Node.js, AWS Lambda, AWS Step Functions, AWS, OpenAI, Anthropic, MCP, Embeddings, Vector Search, React, Next.js, Tailwind CSS, Terraform, 6 years of relevant experience