Portless fulfills e-commerce orders directly from China, shaving months of time and saving you $$$ along the way.
AI Engineer
Location
Worldwide
Posted
7 days ago
Salary
0
Seniority
Mid Level
No structured requirement data.
Job Description
AI Engineer
Portless
Role Description At Portless, we specialize in global delivery solutions for SMBs and enterprise merchants, enabling businesses to ship direct-from-factory from manufacturing hubs like China to destinations worldwide. As an AI Engineer, you will own the design, development, and deployment of AI-powered systems that make our operations faster, our team smarter, and our merchants more successful — from intelligent automation and agentic workflows to LLM integrations embedded across our product and internal tooling. If you're passionate about building AI systems that create real business impact, thrive in fast-moving environments, and want to work at the intersection of logistics and cutting-edge AI, we'd love to meet you. - Design and build AI-powered features across our B2B portal, internal tooling, and merchant-facing products — including LLM integrations, AI agents, and intelligent automations - Translate ambiguous business problems into well-scoped AI solutions, from prompt engineering and RAG pipelines to full agentic workflows - Build, evaluate, and iterate on AI systems using a rigorous experiment-driven approach — tracking quality, latency, and cost tradeoffs - Collaborate closely with product, operations, and engineering teams to identify high-leverage AI opportunities and deliver them end-to-end - Develop internal AI tooling and skill frameworks that empower non-technical teams to leverage AI in their daily workflows - Integrate with third-party AI APIs (Anthropic, OpenAI, etc.) and MCP-based tooling while maintaining security and reliability standards - Maintain observability over deployed AI systems — monitoring for regressions, prompt drift, and model performance degradation - Work independently in a remote environment with a strong sense of ownership and ability to ship with minimal oversight Qualifications - 3+ years of software engineering experience, with at least 1–2 years focused on building production AI or ML systems - Hands-on experience with LLM APIs (Anthropic Claude, OpenAI GPT, etc.) and prompt engineering best practices - Strong programming skills in Python and/or TypeScript/JavaScript; comfortable building both backend services and lightweight frontend interfaces - Experience building RAG pipelines, embedding workflows, or agentic systems using frameworks like LangChain, LlamaIndex, or similar - Familiarity with vector databases (Pinecone, Weaviate, pgvector, etc.) and semantic search patterns - Experience working cross-functionally with non-technical stakeholders to scope and deliver AI projects - Proven ability to evaluate AI output quality and build evals/testing frameworks for LLM-based systems - Logistics, supply chain, or B2B SaaS experience is a strong plus - Experience with MCP (Model Context Protocol), AI agent orchestration, or multi-step tool-use workflows is a bonus
Related Guides
Related Job Pages
More AI Engineer Jobs
Senior Forward Deployed AI Engineer
Omada HealthFounded in 2011, Omada Health is an Internet company with headquarters in San Francisco, California. Recognized by Fast Company magazine as one of the "50 Most Innovative Companies
• Serve as the primary point of contact for department champions across Omada, working with them to understand their day-to-day workflows and identify where AI-assisted automation creates real leverage. • Drive AI adoption across the company by deploying tool bundles that are actually useful, making sure integrations fit how teams work rather than asking teams to adapt to what's technically convenient. • Run a continuous feedback loop: gather usage signals and qualitative input from champions, identify what's working and what's falling flat, and iterate accordingly. • Build lightweight documentation, reference examples, and enablement materials that help non-technical stakeholders understand what's possible and how to request new capabilities. • Represent the needs of end users and champions when making integration decisions; you are their voice in the build process. • Integrate SaaS and internal applications with Omada's MCP ecosystem by building and configuring MCP servers, adding tools, and handling authentication patterns including OAuth and webhooks. • Write skills that expose the right actions and data to AI agents in a clear, composable way. • Compose skills and tools into role-appropriate bundles, scoped to what each team and function actually needs, not everything at once. • Deploy tool bundles to ABAC groups, managing access so the right people get the right capabilities without overprovisioning. • Partner with the Senior IT Engineers, Automation on integrations that span MCP and workflow automation, ensuring handoffs and shared patterns are consistent. • Participate in design reviews for new MCP integrations to catch potential issues early and keep the ecosystem coherent. • Teach and mentor IT team members as you go. Be the SMEs that help us understand and internalize this tech.
Role Description Nous recherchons un(e) ingénieur(e) Forward Deployed (FDE) possédant une expertise approfondie de Google Cloud et de l’IA appliquée afin de travailler directement avec nos clients d’entreprise et de transformer les capacités d’IA de pointe en systèmes prêts pour la production. Ce rôle s’adresse à un(e) ingénieur(e) à l’aise dans des environnements ambigus, capable de coder aux côtés des équipes clients et de prendre en charge des initiatives IA de bout en bout — de la découverte technique à l’architecture, au développement, au déploiement et à la transition opérationnelle. Ce poste est entièrement à distance et peut nécessiter des déplacements occasionnels. Responsibilities - S’intégrer aux équipes d’ingénierie des clients et diriger des ateliers de découverte technique avec les parties prenantes d’affaires, les responsables de l’ingénierie et les équipes de sécurité afin de transformer des problèmes d’affaires ambigus en architectures IA claires et en plans de livraison concrets. - Architecturer, développer et livrer des solutions d’IA agentique prêtes pour la production sur Google Cloud. - Concevoir et mettre en œuvre des pipelines de génération augmentée par récupération (RAG) et des architectures d’ancrage contextuel. - Construire la « couche connective » entre les produits IA de Google et l’infrastructure des clients. - Mettre en œuvre des modèles multi-agents tels que ReAct, l’auto-réflexion et la délégation hiérarchique. - Créer des pipelines d’évaluation haute performance et des cadres d’observabilité pour les systèmes agentiques. - Déboguer la logique des agents et optimiser la sélection des outils dans des environnements en production à fort trafic. - Co-développer avec les équipes d’ingénierie des clients et agir comme promoteur(trice) actif(ve) du développement assisté par IA. - Assurer un transfert structuré vers l’équipe du client, garantissant la prise en charge à long terme. - Rédiger et maintenir à jour la documentation technique, les registres de décisions d’architecture et les résultats d’évaluation. Qualifications - Baccalauréat en génie, en informatique, dans un domaine connexe, ou expérience pratique équivalente. - Plus de 5 ans d’expérience en développement logiciel avec Python, TypeScript ou des langages comparables. - Expérience pratique dans l’architecture et le déploiement de systèmes d’IA sur Google Cloud Platform (GCP). - Expérience démontrée dans le développement de solutions agentiques et alimentées par l’IA en production. - Capacité à voyager jusqu’à 50 % du temps sur les sites des clients. - Excellentes aptitudes en communication. Requirements - Maîtrise de l’IA appliquée à la productivité. - Expérience dans l’intégration de systèmes d’IA avec l’infrastructure TI d’entreprise. - Expérience dans la direction d’ateliers de découverte technique. Benefits - Un régime d’assurance complet, avec la possibilité de choisir le module qui répond le mieux à vos besoins. - Dialogue via Sun Life pour des services de soins de santé virtuels. - Un Compte de dépenses personnel de $500. - Un régime de retraite avec égalisation des contributions à votre REER. - Accès à un programme de vacances flexibles. - Remboursement de technologie personnelle — $30/mois. - Horaires flexibles tout au long de l’année.
Senior AI Systems Engineer
FNTIOUnlock Your Business's Full Potential with FNTIO's Cloud Solutions: Streamline, Scale, and Succeed!
Role Description Du bist die technische Schlüsselfigur in Enterprise-Projekten auf AWS. Du sitzt mit Kunden zusammen, verstehst ihre Herausforderungen und entwirfst Lösungen. Dann orchestrierst du AI Agents, lässt Infrastructure as Code generieren, prüfst den Output kritisch und iterierst. Nicht Zeile für Zeile. Sondern Architektur für Architektur. - Du entwirfst hochverfügbare AWS-Architekturen und setzt sie mit AI-gestütztem IaC um. - Du arbeitest direkt mit Kunden an Cloud-Strategien und Migrationsprojekten. - Du nutzt AI CLI-Tools als Multiplikator: Claude Code, Cursor oder Gemini CLI. - Du mentorst andere Engineers und definierst technische Standards. - Du triffst Architekturentscheidungen und übernimmst Verantwortung für das Ergebnis. Qualifications - Mindestens 5 Jahre Erfahrung mit AWS und Cloud-Architekturen. - AWS Professional Zertifizierung oder vergleichbar. - Erfahrung mit mindestens einem AI CLI-Tool (Claude Code, Cursor, Gemini CLI). - Solide Kenntnisse in IaC (Terraform, CDK oder CloudFormation). - Sicherheitsbewusstsein für Enterprise-Anforderungen. - Du kannst komplexe technische Zusammenhänge verständlich kommunizieren. - Fließend Deutsch und Englisch. Benefits - Flexible Arbeitszeiten und 100% Remotearbeit. - Zugang zu AI-Tools und LLM-Keys. Nicht als Benefit, sondern als Arbeitsmittel. - Echte Enterprise-Projekte mit Ownership. Du baust Produkte, auf die du stolz sein kannst. - AWS-Zertifizierungen und Konferenzen. - Ein Team von ~30 Engineers, das Wissen teilt statt hortet. - Keine Folien-Kultur. Wir arbeiten an der Sache, nicht am Konzept. Company Description FNTIO sind AI-First Systems Engineers für Enterprise. Wir verbinden tiefe Cloud- und AI-Expertise mit Hands-on-Mentalität, um Produkte zu bauen, die Unternehmen wirklich transformieren. Keine Buzzwords, kein Body Leasing. Ergebnisse.
Senior AI Engineer
Ignota LabsIgnota Labs is a pioneering biotechnology company using advanced artificial intelligence to rescue and repurpose promising but abandoned drugs, transforming fai
Senior AI Engineer Hybrid Full time Cambridge, England, United Kingdom As a Senior AI Engineer at Ignota Labs, you will design and build the agentic systems, LLM-powered tools, and cloud infrastructure that will help our scientists identify failed drugs and bring them safely to patients. Your systems will augment and assist human experts at all stages of our business, from identifying high-potential drug programmes to helping to validate new chemistry. Joining Ignota Labs at this stage will give you the ability to have an outsized impact on our efforts to automate some of the knowledge work that goes into drug discovery and development. With each successfully rescued drug, you will have made a direct contribution to bringing medicines to patients who otherwise would not have had access to them. Requirements What Makes This Role Unique Applied: The tools you build will directly enable research that has a tangible path to patient impact. Multi-disciplinary: You’ll work closely with scientists, ML researchers, and engineers, gaining insight into the end-to-end drug discovery and development process. Dynamic: Ignota is a fast-paced, startup environment — every week will bring new challenges and opportunities to learn. Innovative: You’ll work with state-of-the-art AI models and services, deploying them in creative ways to solve complex, real-world R&D problems. What You’ll Do - Design the and build orchestration architecture for multi-modal drug redevelopment workflows. - Collaborate with ML researchers to prototype and deploy experimental models into usable tools. - Build automation and agentic systems to streamline literature review, data extraction, and target identification. - Work with scientists to ensure tools are robust, reproducible, and easy to use. - Continuously improve development, testing, and deployment processes. Who You Are Mission-oriented: You want your engineering work to accelerate life-changing scientific research. Fast learner: You can quickly absorb new technologies, APIs, and scientific concepts. Collaborative: You work effectively with interdisciplinary teams, adapting your communication for technical and non-technical audiences. Curious & versatile: You enjoy working across domains and connecting ideas between them. What You’ll Bring A strong candidate will have most of the following attributes: - Strong Python development experience, writing production-quality, maintainable code. - Experience integrating and orchestrating AI/LLM services via APIs and related tooling. - Experience with agent frameworks such as Pydantic AI, Langgraph, or Crew AI. - Experience leading and managing technical teams. - Experience running and evaluating agentic systems in production. - Strong technical communication skills. - Ability to rapidly prototype and iterate quickly based on feedback. - Comfortable taking high-level research goals and turning them into working solutions. - Familiarity with at least one cloud platform, ideally GCP. Benefits What We Offer - A competitive salary (c. £70-90K depending on experience), performance-based bonus, pension, and equity in a high-growth startup. - Opportunities for rapid career growth and progression as we scale. - A collaborative, flexible, hybrid working environment. We have offices in Cambridge with remote options and tools to support seamless communication. - Vitality health insurance, including mental health, dental, and optical care. - The chance to bring potentially life-saving drugs back to patients - helping improve the lives of millions.



