Senior Software Engineer – Serverless

Description

Runware is looking for a Senior Software Engineer to help build the systems behind its AI platform. This is a remote, full-time role focused on backend APIs, SDKs, developer tools, AI inference orchestration, and high-performance distributed systems. The position is aimed at experienced engineers who enjoy solving complex infrastructure and scalability problems.

The role goes beyond traditional backend development. You will work on AI model integrations, workload orchestration, asynchronous processing, queues, streaming data, cloud and bare-metal infrastructure, performance optimization, reliability, and observability. You will also have ownership of technical projects and help shape how the platform develops.

This could be a strong opportunity for a senior backend or platform engineer who wants to work in AI infrastructure and also contribute to developer-facing products. Runware expects strong PHP or Go skills, experience with distributed systems and scalable APIs, and the ability to lead projects and mentor other engineers. The role is remote-first and requires availability within the European time zone.

Job at a Glance

Job Title	Senior Software Engineer – Serverless
Company	Runware
Location	Remote, European Time Zone
Job Type	Full-Time
Experience	Senior-level
Industry	Artificial Intelligence / Software
Job Category	Software Engineering
Main Focus	Distributed systems, backend APIs, AI inference orchestration and serverless infrastructure

Detailed Role Requirements & Responsibilities

AI Platform Development

The engineer will help design and implement core systems that power Runware’s AI platform.

Responsibilities include:

• Designing and implementing core platform systems
• Building backend services that support AI applications
• Working on systems that make AI integration easier for developers
• Improving the reliability and performance of the platform
• Contributing to technical decisions that affect the wider product

The role combines backend engineering with AI infrastructure, so candidates should be comfortable working on systems where software performance and scalability are important.

Backend APIs and Developer Tools

A significant part of the position involves building tools that developers use to integrate AI capabilities.

You may work on:

• Backend APIs
• SDKs
• Developer tools
• Dashboards
• Documentation and tooling
• Developer-facing experiences

The goal is to make AI integration easier while keeping the underlying systems reliable and maintainable.

AI Model Integration

The role includes working with different AI model types and improving how they operate within the platform.

Responsibilities include:

• Integrating image models
• Optimizing video model integrations
• Supporting additional modalities such as audio
• Supporting custom large language models
• Improving how AI inference workloads are handled

This makes the role relevant to engineers interested in the software infrastructure behind AI applications rather than only model development.

Inference Orchestration

Runware needs scalable systems to coordinate AI inference workloads.

The engineer will work on:

• Inference orchestration
• Workload optimization
• Scalable architectures
• Asynchronous workloads
• Queues
• Streaming data
• Performance optimization

These responsibilities require a good understanding of distributed systems and how different services communicate and operate under changing workloads.

Cloud and Bare-Metal Infrastructure

The position requires experience working with both cloud and bare-metal infrastructure.

Candidates should be comfortable thinking about:

• Infrastructure architecture
• Resource utilization
• Performance
• Scalability
• Reliability
• Production operations

This combination is useful for engineers who have worked with systems where infrastructure decisions directly affect application performance.

Performance, Reliability and Observability

The role involves improving how Runware’s platform performs and operates in production.

You will work with platform and infrastructure teams to improve:

• Performance
• Reliability
• Observability
• Scalability
• System efficiency

Being able to investigate bottlenecks and understand how a distributed system behaves in production will be important in this position.

Technical Leadership

This is a senior position with leadership responsibilities.

The engineer will:

• Lead technical projects
• Participate in architectural discussions
• Help shape long-term technical direction
• Review code and system designs
• Mentor other engineers
• Help improve engineering standards
• Balance short-term delivery with longer-term technical goals

This means the position is not limited to implementing tickets. Candidates should be prepared to demonstrate ownership and technical judgment.

Required Skills and Experience

The core requirements include:

• Deep experience building distributed and high-performance systems
• Strong programming skills in PHP or Go
• Experience designing and delivering scalable backend systems
• Experience building backend APIs
• Understanding of asynchronous workloads
• Experience with queues and streaming data
• Experience working with cloud and bare-metal infrastructure
• Strong understanding of system design
• Knowledge of performance optimization and scalability principles
• Ability to lead technical projects
• Strong communication skills
• Experience mentoring engineers
• Ability to solve problems proactively and think about long-term technical direction
• Availability within the European time zone

Skills That Can Strengthen Your Application

The posting places particular emphasis on distributed and high-performance systems, so experience in related areas can strengthen your application.

Useful additional experience includes:

• Serverless platforms
• AWS Lambda
• GCP Cloud Run
• Cloudflare Workers
• Knative
• AI/ML infrastructure
• GPU scheduling
• Workload orchestration
• Inference systems
• Model deployment
• Developer platforms
• Cloud infrastructure
• High-throughput backend systems
• Observability and monitoring

These skills should be presented as additional strengths unless they are specifically required by the employer.

Industry Context & Career Advice

AI infrastructure is becoming an important area of software engineering as companies need reliable systems to run increasingly complex AI workloads. Developers want to use AI models without having to manage GPUs, servers, queues, scaling, and other infrastructure themselves.

That creates demand for engineers who can connect application development with infrastructure and distributed systems. This Runware role sits directly in that space, combining backend engineering, AI inference, cloud infrastructure, performance optimization, and developer experience.

For applicants, strong distributed-systems experience can be more valuable than simply having a list of AI keywords on a resume. Show examples of systems you have designed, scaled, optimized, or operated in production.

If you have experience with asynchronous processing, queues, streaming data, high-throughput APIs, workload scheduling, or infrastructure optimization, explain the problem you solved and the result. These examples can demonstrate the type of engineering judgment the role requires.

What to Highlight on Your Resume

For this position, make the following areas easy to find on your resume:

• Senior backend engineering experience
• PHP or Go
• Distributed systems
• High-performance systems
• Scalable backend APIs
• System architecture
• Asynchronous processing
• Queues
• Streaming data
• Cloud infrastructure
• Bare-metal infrastructure
• AI/ML infrastructure
• Inference systems
• Performance optimization
• Reliability and observability
• Serverless architecture
• Technical project ownership
• Mentoring and code reviews

When describing your projects, focus on scale and outcomes. Instead of simply writing that you “developed backend APIs,” explain what the APIs supported, how much traffic or data they handled if you can provide accurate figures, and what you improved.

A stronger resume bullet for this position could be:

Designed and delivered scalable backend services using Go, supporting distributed workloads and asynchronous processing while improving system performance, reliability, and observability.

Customize this example with your actual technology, metrics, and results.

Interview Preparation

How would you design a high-performance distributed system?

Be prepared to discuss system architecture, scalability, communication between services, data flow, failure handling, monitoring, and performance bottlenecks.

How would you design a scalable backend API?

Think about API structure, authentication, rate limiting, caching, database access, scalability, error handling, monitoring, and backward compatibility.

How do asynchronous workloads and queues work?

Review concepts such as producers and consumers, retries, message ordering, duplicate processing, dead-letter queues, and failure recovery.

How would you optimize a system that is becoming too slow?

Explain how you would identify the bottleneck before changing the architecture. Discuss profiling, metrics, tracing, database performance, network latency, resource utilization, caching, and workload patterns.

Tell us about a distributed system you have built.

Choose a real project and explain the architecture, your specific contribution, the technical challenges, and how the system performed in production.

How would you approach AI inference orchestration?

Think about workload routing, scheduling, resource availability, queues, model selection, latency, scaling, failure handling, and infrastructure utilization.

Tell us about a technical project you led.

Prepare an example that shows how you moved from requirements and system design to implementation and production. Explain the decisions you made and how you worked with other engineers.

How do you mentor other engineers?

Be ready to discuss code reviews, design reviews, technical guidance, documentation, knowledge sharing, and how you help other engineers improve.

Advice for Applicants

This role is best suited to a senior engineer with strong backend and distributed-systems experience who wants to work on AI infrastructure. The most important part of your application should be evidence that you can design, build, and operate complex systems at scale.

PHP or Go experience is important, so make your strongest experience with either language easy to find. You should also clearly demonstrate your work with scalable APIs, asynchronous workloads, queues, streaming data, and cloud or bare-metal infrastructure.

You do not need to present every serverless technology as a requirement. The posting emphasizes broad systems experience, while specific serverless technologies such as AWS Lambda, GCP Cloud Run, Cloudflare Workers, and Knative are useful additional skills.

The remote arrangement is also worth checking carefully. The position is remote-first, but the listing requires availability within the European time zone.

The strongest application will position you as someone who can combine strong backend engineering, distributed-systems knowledge, technical leadership, and an understanding of how to build reliable infrastructure for AI workloads.

Benefits

Runware lists several benefits for the role, including:

• Generous paid time off
• Stock options
• Remote-first work
• Flexible working hours outside core collaboration periods
• Paid family leave
• Twice-yearly company retreats