About this role.
Zartis is seeking a Senior Backend Engineer to build and operate production-grade Generative AI applications for a technology-sector project. The role combines Node.js and TypeScript backend development with AWS cloud architecture, including serverless, containerized, and Kubernetes-based workloads. The engineer will integrate Amazon Bedrock and LLM patterns such as RAG, tool calling, context management, prompting, and knowledge indexing. Success requires ownership of production concerns including quality, latency, cost, security, traceability, observability, resilience, and collaboration within a distributed remote team.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
4/5Autonomy Level
5/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Sample interview questions
I would separate ingestion, indexing, retrieval, generation, and evaluation concerns. Documents would be securely ingested and chunked with metadata, embedded into an appropriate vector store, and retrieved with authorization-aware filtering; an orchestration service would construct prompts and call Bedrock. I would add tracing, retrieval and answer-quality evaluation, caching, rate limits, fallback behavior, and dashboards for latency, token usage, error rates, and cost.
Lambda is effective for event-driven workloads, intermittent traffic, and operational simplicity, but cold starts, runtime limits, connection management, and long-running streaming workloads can be constraints. ECS or EKS provides more control over networking, persistent processes, streaming, dependency packaging, and scaling behavior, although it adds operational overhead. I would choose based on traffic predictability, latency objectives, workload duration, operational maturity, and cost profile.
I would first establish measurable quality criteria and collect representative production-safe traces and user feedback. Then I would evaluate retrieval relevance, prompt construction, context size, model selection, tool-call success, hallucination rates, and fallback behavior through offline test sets and controlled releases. Improvements should be versioned, monitored, and validated against latency and token-cost budgets before broad rollout.
I would apply least-privilege IAM, network segmentation, encryption in transit and at rest, secret management, and strict tenant-level authorization for data retrieval. Sensitive data should be minimized or redacted before model calls where possible, while logs and traces must avoid exposing protected content. I would also implement audit trails, input validation, output safety controls, dependency security scanning, and retention policies aligned with applicable compliance requirements.
I begin by clarifying business outcomes, expected usage, service-level objectives, and non-negotiable security or compliance constraints. I compare viable options using measurable criteria such as implementation effort, operational burden, latency, resilience, unit economics, and future extensibility, then document the decision and assumptions in an ADR. I favor the simplest approach that meets current requirements while defining clear triggers for when the architecture should evolve.
The company and our mission:
Zartis is a global AI transformation and technology consulting partner where talented engineers and technologists work on cutting edge innovation. We partner with ambitious organizations to design, build, and scale technology solutions that deliver real impact.
Our teams bring deep expertise in AI driven platforms, secure API architectures, and cloud native engineering. You will work on meaningful projects that accelerate the adoption of advanced technologies, from strategy and discovery through to full product delivery, helping turn complex challenges into measurable outcomes.
With engineering hubs across EMEA and LATAM, and long term partnerships in financial services, healthcare and life sciences, and energy and climate, we offer opportunities to work on projects that truly matter. Here, you will not just build technology, you will drive business impact and grow your career alongside industry leaders.
We are looking for a Senior Backend Engineer to work on a project in the Tech industry.
The project:
You will join a distributed engineering team building and evolving production-grade applications powered by Generative AI.
This is a hands-on backend engineering role combining Node.js/TypeScript, AWS cloud architecture, and Generative AI. You will design and develop scalable backend services, integrate LLM capabilities into production systems, and contribute to the architectural decisions behind reliable AI-powered products.
A key part of the challenge is going beyond the initial AI integration. You will help ensure these systems perform reliably in production, addressing challenges around response quality, latency, cost, security, traceability, observability, and resilience.
We are looking for an experienced engineer who can take ownership, make sound technical decisions, and apply strong software engineering principles to the specific challenges of building and operating AI-powered applications.
What you will do:
Design, develop, and deploy scalable backend applications using Node.js and TypeScript.
Integrate Generative AI and LLM capabilities into production-grade applications and services.
Design and operate cloud-native architectures on AWS, working across serverless and container-based environments.
Build and deploy containerized workloads using technologies such as EC2, ECS/EKS, and Kubernetes.
Build LLM-powered capabilities using Amazon Bedrock and patterns including RAG, tool calling, context management, prompting, and knowledge indexing.
Design solutions that address the real-world challenges of production AI, including response quality, latency, cost efficiency, traceability, and observability.
Apply engineering best practices around scalability, security, resilience, and maintainability.
Contribute to backend and cloud architecture, making informed technical decisions and evaluating trade-offs.
Collaborate with engineering and product stakeholders to take AI-powered capabilities from design through to reliable production delivery.
What you will bring:
Extensive professional experience building backend applications with Node.js and TypeScript.
Demonstrable experience designing, developing, and deploying Generative AI capabilities in production — beyond prototypes or proof-of-concepts.
Strong hands-on experience designing and operating solutions on AWS.
Experience with serverless and container-based architectures, including EC2, ECS/EKS, Kubernetes, or equivalent AWS technologies.
Hands-on experience with Amazon Bedrock and/or production LLM applications within the AWS ecosystem.
Practical experience implementing LLM application patterns such as Retrieval-Augmented Generation (RAG), tool calling, context management, prompting, and knowledge indexing.
Strong understanding of the challenges involved in running AI-powered applications in production, including quality, latency, cost, traceability, and observability.
Proven ability to design scalable, secure, resilient, and maintainable backend systems.
Experience making technical and architectural decisions and evaluating trade-offs in production environments.
Strong communication and collaboration skills, with a proactive approach to ownership and problem-solving.
What we offer:
100% Remote Work
WFH allowance: Monthly payment as financial support for remote working.
Career Growth: We have established a career development program accessible for all employees with a 360º feedback that will help us to guide you in your career progression.
Training: For Tech training at Zartis, you have time allocated during the week at your disposal. You can request from a variety of options, such as online courses (from Pluralsight and Educative.io, for example), English classes, books, conferences, and events.
Mentoring Program: You can become a mentor in Zartis or you can receive mentorship, or both.
Zartis Wellbeing Hub (Kara Connect): A platform that provides sessions with a range of specialists, including mental health professionals, nutritionists, physiotherapists, fitness coaches, and webinars with such professionals as well.
Multicultural working environment: We organize tech events, webinars, parties, and activities to do online team-building games and contests.
Annual salary information is not provided for this position. Explore salary ranges for similar roles in our Salary Directory ›
Upload your resume now
- To unlock remote work opportunities and be discovered by global employers.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
