Machine Learning Engineer, Reliability

The Consensus; New Zealand; On-site; NZD 120,000 - 180,000; Full time

Job summary

fal is building a large-scale generative media platform and seeks an ML Engineering / Site Reliability Engineer to own reliability, security, and safety of model APIs. You will ensure uptime, latency, and safety across thousands of productions endpoints, while tracing failures and improving deployment pipelines.

The role combines production ML engineering with site reliability practices, requiring deep knowledge of modern ML systems, security, and scalable infrastructure.

Qualifications

• 3+ years of professional experience in ML engineering or SRE roles.
• Experience operating production ML or high-scale API systems with on-call ownership.

Responsibilities

• Own availability, latency, and throughput SLOs for a fleet of model APIs serving production traffic at scale.
• Build monitoring, alerting, and observability to catch ML-specific failures and degradation.
• Harden deployment workflows with canary releases, shadow testing, and automated rollbacks.
• Drive security posture of the model fleet including abuse detection and rate limiting.
• Operationalize safety systems for generative media and guardrails during inference.
• Lead incident response for outages and postmortems to prevent recurrence.
• Improve capacity planning, autoscaling, and GPU efficiency for variable traffic.
• Collaborate with model and infra teams to embed reliability requirements in onboarding of new models.

Skills

Python

Distributed systems

Observability

Incident management

On-call ownership

Networking

ML systems

Tools

PyTorch / torch

diffusers

Kubernetes

GPU inference cluster

Fal Python SDK

Job description

fal is the generative media ecosystem powering the next generation of AI products. We build the infrastructure, tools, and model access that teams need to move from idea to production, and do it at scale without compromise. For developers and enterprises, fal is the foundation that makes generative media not just possible, but practical: a unified platform where high-performance inference, orchestration, and observability come together to unlock new categories of AI-native products.

As generative media reshapes industries across a market projected to grow by hundreds of billions over the next decade, fal is becoming the ecosystem that ambitious teams build on.

This is a hybrid ML Engineering / Site Reliability Engineering role. You will own the reliability, security, and safety of fal's fleet of generative media model APIs, the production endpoints that thousands of developers and enterprises depend on every day. Your mission is simple to state and hard to do: keep a large, fast-moving fleet of image, video, and audio model APIs available, performant, secure, and safe at all times.

You understand both how generative models work and how production systems fail. You're as comfortable debugging a misbehaving diffusion pipeline as you are tracing a latency regression through an inference stack, and you treat model-specific failure modes; degraded output quality, drift, unsafe generations, abuse patterns; as first-class reliability concerns alongside uptime and latency.

This role will need to be based in India, Australia, or New Zealand

What you'll do

• Own availability, latency, and throughput SLOs across a large fleet of generative media model APIs serving production traffic at scale
• Build the monitoring, alerting, and observability needed to catch ML-specific failures, output quality degradation, pipeline breakage, model regressions before customers do
• Harden model deployment workflows with canary releases, shadow testing, automated rollbacks, and validation gates so new model versions ship safely
• Drive the security posture of the model fleet: secure model serving, abuse and misuse detection, rate limiting, and protection against adversarial usage patterns
• Operationalize safety systems for generative media, content moderation pipelines, safety classifiers, and guardrails that run reliably at inference time without compromising performance
• Lead incident response for model API outages and degradations, run postmortems, and drive the engineering work that prevents recurrence
• Improve capacity planning, autoscaling, and GPU fleet efficiency for inference workloads under highly variable traffic
• Partner with model and infrastructure teams to make reliability, security, and safety requirements part of how new models get onboarded to the platform

Tech

• You will have access to our massive GPU cluster for inference and evaluation
• Some core technologies we use include Python, torch, diffusers, Kubernetes, and the fal Python SDK
• You’ll work alongside a team dedicated to quickly iterating on and deploying new AI breakthroughs — your job is to make sure that speed never comes at the cost of reliability

What we’re looking for

• 3+ years of professional experience, with 1 year experience operating production ML or high-scale API systems, ideally with on-call ownership
• Strong systems fundamentals: distributed systems, networking, observability, and incident management
• Working knowledge of modern generative models (diffusion, transformers) and their failure modes in production
• Familiarity with security and safety practices for ML systems ,abuse prevention, content safety, or trust & safety engineering experience is a strong plus
• A bias toward automation, measurement, and blameless postmortems

Location:

Remote (India, Australia, New Zealand)