Software Engineer – Agentic System Development

🕒 il y a 1 jour

🇺🇸 États-Unis – Télétravail

⏰ Temps Plein

🟡 Intermédiaire

🟠 Senior

🧑‍💻 Développeur Full-Stack

👻 Score fantôme 10%

Ce que ça veut dire : la probabilité que personne ne recrute vraiment pour cette offre.Comment le lire : 60 % ou plus, on pense que c'est une offre fantôme. Un score plus bas est moins inquiétant.Comment on la calcule : ancienneté, republications, postes ouverts vs taille de l'équipe, rapidité de clôture, et si le salaire est indiqué.À noter : une estimation à partir de données publiques, pas un jugement sur l'entreprise. De vraies offres peuvent avoir un score élevé, alors prenez-le comme un indice, pas comme un fait.

Postuler Maintenant

Trouver des Emplois à Distance Similaires

STARLIMS

Site WebLinkedInTous les Emplois

201 - 500 employés

Fondée en 1986

🍽️ Alimentation et boissons

📦 Logistique

🏭 Fabrication

Food & Beverage • Logistics • Manufacturing

STARLIMS est un fournisseur leader de systèmes de gestion de l'information de laboratoire (LIMS) et de solutions informatiques, desservant divers secteurs, y compris les sciences de la vie, les biens de consommation et la santé publique. Avec plus de 1 100 clients dans plus de 85 pays, STARLIMS simplifie les opérations de laboratoire, améliore l'efficacité et renforce l'intégrité des données grâce à ses plateformes complètes. L'entreprise propose des solutions innovantes depuis sa création en 1986, aidant les laboratoires à optimiser leurs processus de R&D et de contrôle qualité.

Description

• Design and build the runtime for agents, including planning and execution loops, tool calling, state management, durable execution, and failure recovery • Build safe agent access to platform data and external systems • Design coordination, delegation, and handoff across agents and workflows • Make agent behavior versionable, testable, measurable, and regression-safe across releases • Build reusable primitives so new agents can be configured rather than rebuilt • Convert domain workflows from expert conversations into working agents • Ground agent decisions and outputs in authoritative enterprise data • Implement human-in-the-loop approval gates, override capture, uncertainty handling, and evidence for decisions • Use user corrections and overrides to improve agents • Build evaluation harnesses for multi-step agent behavior • Define production metrics for agent quality, reliability, latency, cost, and human intervention • Implement guardrails, fallbacks, timeouts, cost ceilings, observability, and tracing • Design safeguards against prompt injection, unsafe tool use, excessive permissions, and data leakage • Manage prompt evolution, model drift, and non-determinism across releases • Integrate agents with platform APIs and third-party enterprise systems • Build retrieval and context pipelines for reliable, permission-aware agent context • Design controlled execution paths with complete, traceable audit trails • Build and operate backend services on AWS • Own significant parts of system architecture and contribute to technical decisions • Contribute to infrastructure-as-code and deployment pipelines

🎯 Exigences

• 6+ years of software engineering experience, including production systems • Strong understanding of LLM behavior, limitations, and failure modes, especially how errors compound across a multi-step run • Experience with LLM APIs, tool and function calling, and designing planning and execution loops • Experience evaluating and debugging non-deterministic systems • Solid backend and cloud experience (AWS or equivalent) • Proficiency in TypeScript and/or Python • Comfortable debugging across distributed and non-deterministic systems • Comfortable making explicit tradeoffs between accuracy, latency, reliability, and cost • Comfortable working in ambiguous problem spaces where the right architecture isn't obvious yet • Comfortable owning production systems end-to-end • Comfortable choosing conventional software over AI when AI isn't the right solution • Nice to have: C#, Microsoft .NET Framework • Nice to have: Tool and interop protocols such as MCP • Nice to have: Production LLM systems, including tool-using or multi-step agentic workflows beyond simple prompting and chat interfaces • Nice to have: Evaluation pipelines and metrics built specifically for agentic systems • Nice to have: Experience in regulated or domain-heavy systems (validation, audit trails, controlled change) • Nice to have: Retrieval and grounding techniques for supplying agent context • Nice to have: Workflow and durable-execution platforms (Temporal, Step Functions, n8n, etc.) • Nice to have: Containerization and orchestration (ECS, EKS, Kubernetes) • Nice to have: Infrastructure as Code (Terraform or similar)

🏖️ Avantages

• Equal Opportunity Employer • Consideration for employment without regard to race, creed, religion, color, national or ethnic origin, citizenship, sex, sexual orientation, gender identity and expression, genetic information, veteran status, age or disability status

📊 Vérifiez votre score de CV pour ce poste

Améliorez vos chances d'obtenir un entretien en vérifiant votre score de CV avant de postuler.

Télécharger le CV