דרושים » הנדסה » LLM & Agentic Systems Engineer

We are seeking a Backend Team Lead to spearhead the development of ludeo.ai, our GenAI-powered product that enables users to generate interactive (gaming experiences) directly from prompts or video content. This is a high-impact leadership role at the intersection of backend architecture, multimodal AI, and real-time systems. You will architect and lead the AI engine that transforms unstructured inputs (text/video) into structured, interactive gaming playable moments.

What Youll Do

Lead & Mentor: Build and manage a high-performing backend/AI engineering team, drive architectural decisions, and foster rapid innovation while maintaining production-grade reliability.
Design AI-Native Systems: Architect scalable microservices powering complex AI workflows. Design and implement Retrieval-Augmented Generation (RAG) pipelines, embedding strategies, and vector database infrastructure (e.g., Pinecone, Weaviate, Milvus, PGVector). Optimize retrieval, prompt orchestration, latency, and cost.
Agentic Workflows: Design multi-agent systems using planner/executor/tool-calling patterns. Implement stateful, multi-step AI workflows with frameworks such as LangChain, CrewAI, AutoGen, or similar. Build evaluation, observability, and safety mechanisms for LLM systems.
Multimodal AI: Integrate multimodal models (vision + text) to understand video and translate it into structured form.
Scale & Infrastructure: Ensure robustness, security, and high availability on AWS/Kubernetes. Design distributed systems that handle real-time data and AI workloads efficiently.
Collaborate: Work closely with Product and Design to translate GenAI capabilities into stable, scalable production features.

We are seeking an exceptional Backend Engineer to join our Platform Group, where you will architect and develop shared infrastructure components that power Semperis's enterprise security and identity products. This is a highly collaborative role requiring both technical excellence and strong cross-functional partnership skills.
What You'll Do:
As a Backend Engineer on our Core Platform team, you will:
Design and build shared platform components used across multiple product teams, ensuring scalability, reliability, and maintainability
Architect distributed systems using microservices and event-driven patterns that support enterprise-scale workloads
Own critical backend services from conception through deployment, including code quality, performance optimization, and operational excellence
Collaborate extensively with product engineers, DevOps, and architects to define platform capabilities and technical standards
Drive technical initiatives that improve developer productivity, system observability, and platform resilience
Contribute to architectural decisions and establish best practices for backend development across the organization
Analyze system performance and data patterns to identify optimization opportunities and inform future platform investments

we are seeking a Hands-on Architect to design, build, and evolve the core of next-generation AI cybersecurity platform.This is not an ivory-tower role; it is for a builder at heart.
You will write code, build functional prototypes, and own critical services from inception to production.
This role demands a unique blend of deep, code-level execution with a broad, system-wide architectural vision that spans our entire data, cloud, and AI stack.
Responsibilities:
Rapidly code and build functional proofs of concept (PoCs) and prototypes to explore and validate new architectures, data platforms, data processing frameworks, and GenAI capabilities.
Validate technical feasibility, scalability, and business impact through working software, not just diagrams or documents.
Partner closely with engineering, product and data science teams to translate emerging technologies into production-ready, scalable systems.
Lead architecture design reviews, proactively identify scalability and performance bottlenecks, and embed security principles into the design process from day one.
Serve as a technical leader and mentor, elevating the team's skills through pair programming, in-depth code reviews, and deep-dive sessions on system design and software craftsmanship.

We are looking for a highly skilled and motivated Senior II Software Engineer to join the Operational Experience engineering team. The team is part of the Customer Experience group, which is responsible for the platform, tools, and customer-facing experiences that power how our customers interact with our ecosystem. This is a high-impact, hands-on role, in which youll be working closely with product managers, designers, customer-facing teams, and engineering partners across the company.

You will operate at the intersection of backend engineering, data-intensive systems, platform development, and customer experience. The ideal candidate brings strong expertise in Node.js and TypeScript, along with deep experience working with large-scale data stores, event-driven pipelines, data models, and high-throughput infrastructure. You will work closely with cross-functional partners to design and implement robust backend services, data-access patterns, and operational workflows that power the portal and internal tools. As we invest heavily in Agentic AI, you will also play a central role in shaping and implementing AI-driven capabilities across the platform. While the role is primarily backend, you will occasionally contribute across the full stack when it supports end-to-end delivery.

If you enjoy owning complex problems end to end, improving systems at scale, and building experiences that bring real value to customers, we would love to meet you.

What you'll be doing:
Drive technical direction and architecture within the OX team and across the broader CX organization. You will proactively identify opportunities to improve performance, resilience, cost, scalability, and developer experience, primarily in backend systems but with influence across the stack.
Lead the development of AI-driven and Agentic AI capabilities. Define how LLMs integrate into our platform, build AI-powered workflows, and establish strong engineering patterns for safe and reliable adoption.
Own and evolve the data foundations behind the portal. Optimize pipelines, improve data quality and freshness, and design resilient data-access patterns across Snowflake, Elasticsearch, Kafka, Redis, MySQL, and related systems.
Work closely with product, design, customer-facing teams, and partner engineering groups. Turn ambiguous problems into clear execution plans and ensure alignment with customer and business goals.
Shape shared standards and platform best practices. Guide other teams on backend services, data integration patterns, portal development approaches, and AI-enabled workflows.
Mentor and elevate engineers across the CX group. Promote engineering excellence, share knowledge openly, and help teams adopt effective modern development practices.
Own delivery of high-impact initiatives. Contribute hands-on when needed, remove blockers, maintain execution momentum, and drive projects from concept to production.

we are looking for an AI Engineer to lead our MLOps team and take full ownership of our machine learning infrastructure used to train, evaluate, and deploy our state-of-the-art computer vision models. In this role, you will work closely with other team leads and Product to plan and build the future of core AI platform. You will help define technical direction, make long-term architectural decisions, and translate company goals into executable plans, directly impacting ability to scale its AI capabilities and the overall success of the company.
Responsibilities

Manage and lead the MLOps team, including mentoring, professional development, and day-to-day technical guidance
Plan and own quarterly roadmaps, sprint planning, task breakdown, and execution, ensuring alignment with company and product priorities
Design, build, maintain, and evolve ML infrastructure for training, evaluation, and deployment of computer vision models
Own the end-to-end ML lifecycle in production, including experimentation workflows, training orchestration, model versioning, deployment, and monitoring
Balance delivery and technical excellence by making architectural decisions and enforcing engineering best practices
Work closely with research, data, product, and platform teams to move models reliably from research to production
Actively contribute code to critical components and review design and implementation across the team
Evaluate and introduce new technologies and tooling to improve scalability, reliability, and developer productivity

Your Career The SASE Platform team builds and operates highly available, secure, and globally distributed services that protect users, applications, and data for some of the worlds largest enterprises. Our mission is to deliver cloud-native security and networking capabilities that seamlessly converge networking and security at scale. As enterprises accelerate adoption of cloud, remote work, and AI-driven workloads, the need for resilient, observable, and secure SASE platforms has never been greater. As an SRE, you will play a critical role in ensuring our platform is reliable, scalable, performant, and secure from day one. Your Impact As a Site Reliability Engineer, you will be an integral part of the product and platform lifecycle, partnering closely with software engineers, security experts, and infrastructure teams. You will: Collaborate with development teams to embed reliability, scalability, and operability into services from the earliest design stages Design, review, and evolve cloud-native architectures to improve availability, performance, cost efficiency, and fault tolerance Build and operate automation for provisioning, deploying, and managing infrastructure at global scale using Infrastructure as Code Improve CI/CD pipelines and release processes to enable safe, fast, and repeatable deployments Drive observability best practices, including metrics, logs, traces, SLIs/SLOs, and data-driven incident analysis Participate in on-call rotations, continuously reducing MTTR through automation, runbooks, and proactive reliability improvements Mentor and guide engineers on large-scale cloud and SASE deployments, fostering a strong SRE culture Participate in architecture and design reviews, bringing a reliability and operational excellence mindset Champion reliability, security, and operational maturity across the organization.

Required Software Developer
As a Software Developer you will be responsible to:
Play a key role in designing and implementing infrastructure solutions to support our development and deployment processes.This role requires a versatile individual with strong technical skills, an out-of-the-box thinker, and a passion for solving challenging problems in cloud-based environments.
As part of the role, you will also collaborate on integrating and enabling modern AI-powered tools and services within the development ecosystem, helping teams adopt intelligent automation and emerging technologies where they add clear value.
Develop, maintain, and optimize Node.js -based services and tools for cloud platforms (AWS preferred).
Design and implement scalable and secure infrastructure solutions, leveraging modern cloud technologies.
Build and maintain APIs, microservices, and server-side applications using Node.js
Collaborate with cross-functional teams to integrate CI/CD pipelines and improve deployment efficiency.
Troubleshoot and resolve technical bottlenecks in cloud-based systems.
Contribute to system architecture design and ensure best practices are followed.
Stay up-to-date with emerging technologies and trends to continuously improve development and deployment processes.

Were looking for a Senior Software Engineer to join the AZ Team in Tel Aviv - a group of passionate developers building the secure, scalable backbone of our Customer Experience (CX) Platform.

As a key member of the AZ Team, youll play a pivotal role in shaping the foundations of our CX Platform - driving features and architectural decisions from concept to production-grade solutions. Youll design and build secure, scalable systems for user management, authentication, authorization, and data access that serve thousands of developers across us.

You will:

Design, develop, and build platform-wide authentication and authorization services, creating a cohesive identity fabric that integrates seamlessly with multiple identity vendors and systems.

Lead the evolution of the data consumption layer, enabling governed, efficient, and context-aware access to data across the CX ecosystem.

Drive architectural decisions from concept to production, ensuring solutions are secure, scalable, and optimized for both developer experience and operational excellence.

Leverage AI and automation to enhance access control, anomaly detection, and developer productivity - turning complex platform insights into actionable intelligence.

Collaborate cross-functionally with product, data, and infrastructure teams to build interoperable solutions that power our next-generation developer platform.

Influence platform-wide engineering standards, promoting robust design, observability, and maintainability across services.

Champion developer experience, crafting APIs, SDKs, and tools that simplify integration and accelerate innovation.

Mentor and guide engineers, fostering a culture of technical depth, curiosity, and impact-driven innovation.

Required Software Engineer - Al Platform
What this role is really about:
You're building our AI platform. The internal system that powers AI capabilities across Product, Customer Success, Sales, Operations, Data, and IT.
This is a full-stack role where you'll own features end-to-end: design React interfaces for AI workflows, build Lambda functions that orchestrate multi-agent processes, integrate with enterprise systems (Salesforce, Workato, Snowflake), and optimize costs and performance at scale. You'll work with cutting-edge AI while building production-grade systems that handle real business operations.
If you want to build something that directly enables business growth, work across the full stack with modern tech, and have ownership over a platform that the entire company depends on, this is your opportunity.
Job responsibilities:
Build core AI platform services - Design and implement agent orchestration, prompt management, RAG, Connectors, and evaluation pipelines that power AI experiences across the company.
Develop complex agentic process - Develop a multi-step workflow that coordinates tools and services with proper observability, guardrails, and cost controls (using OpenAI Agent SDK, LangGraph, or a similar framework).
Build LLM evaluation and optimization process -Develop evaluation harnesses, offline/online experiments, prompt-testing frameworks, and dashboards to balance quality, latency, and spend across all AI services.

We are looking for an AI Builder to design, build, and maintain agentic AI-driven workflows that streamline and automate internal business processes across the company.
This role focuses on initiating and orchestrating AI agents, integrating them with existing systems, and reducing manual effort across Sales, Marketing, Order Management, Finance, HR, and more.
You will work closely with the Information Systems team and business stakeholders to turn repetitive, human-dependent processes into reliable, AI-powered flows.
This is a hands-on builder role, not a research or pure data science position.
Key Responsibilities:
Agentic AI & Automation:
Design and implement agent-based AI workflows to automate internal processes end-to-end
Build multi-step AI agents capable of:
Decision-making
Tool usage (APIs, SaaS tools, internal systems)
Escalation and exception handling
Continuously optimize AI flows to reduce human involvement while maintaining control and auditability
AI Tooling & Platforms:
Implement solutions using Agentic AI platforms, tools and frameworks, such as: OpenAI / Azure OpenAI / Copilot Studio / Gemini Enterprise, AWS bedrock (AgentCore), SFDC Agentforce
Low-code / no-code automation tools with AI capabilities (e.g., Make, Workato, UiPath, n8n)
Select and evaluate new AI tools to support internal automation initiatives
Systems Integration:
Integrate AI agents with internal systems such as: CRM (SFDC), ERP (NetSuite), ticketing systems (Jira)
Identity and access management
Monitoring, logging, and knowledge bases
Build and consume APIs to enable agent actions and data retrieval
Governance, Reliability & Security:
Ensure AI workflows comply with security, privacy, and compliance requirements
Implement guardrails, approvals, logging, and human-in-the-loop mechanisms where needed
Monitor AI performance, errors, hallucinations, and drift
Collaboration & Enablement:
Partner with business owners to identify automation opportunities
Translate business requirements into AI-driven solutions
Document AI flows, decision logic, and operational runbooks
Educate internal teams on AI capabilities and limitations.