Senior Machine Learning Engineer

StartApp, inc.; Warszawa; On-site; PLN 180,000 - 240,000; Full time

Job summary

A leading mobile marketing company in Poland seeks a Machine Learning Engineer to design and develop low-latency algorithm inference services that handle billions of daily requests. The ideal candidate will possess a B.Sc. or M.Sc. in Computer Science and have strong expertise in Python and backend systems. This role offers an opportunity to work closely with data scientists and drive critical systems that impact product performance.

Benefits

Fast-paced, collaborative work environment

Full ownership of your domain

Opportunity to solve high-stakes problems

Qualifications

• 5+ years of experience building high-performance backend or ML inference systems.
• Strong understanding of model deployment practices and real-time monitoring.
• Passion for performance, clean architecture, and impactful systems.

Responsibilities

• Own and lead the design and development of low-latency algorithm inference services.
• Collaborate closely with data scientists to deploy models in production.
• Continuously optimize latency, throughput, and cost−efficiency using modern tools.

Skills

Python

Machine Learning

Backend systems

Real-time frameworks

Cloud environments

NoSQL databases

Education

B.Sc. or M.Sc. in Computer Science or related field

Tools

FastAPI

Terraform

Kafka

Kubernetes

Prometheus

Grafana

Job description

Description

Start.io, a leading mobile marketing and audience platform, empowers the app ecosystem with cutting-edge solutions in mobile marketing, audience building, and monetization. With integration into over 500,000 monthly active apps and a global reach, Start.io leverages first-party data to deliver impactful and scalable advertising solutions.

We’re looking for a highly skilled, independent, and driven Machine Learning Engineer to lead the design and development of our next-generation real-time inference services - the core engine powering Start.io’s algorithmic decision‑making at scale. This is a rare opportunity to own the system at the heart of our product, serving billions of daily requests across mobile apps, with tight latency and performance constraints.

Start.io is a mobile marketing and audience platform. Start.io empowers the mobile app ecosystem, simplifying mobile marketing, audience building, and mobile monetization. With direct integration into over 500,000 mobile apps, our platform processes enormous volumes of first-party data to drive intelligent, real-time decisions that fuel growth for our partners.

You’ll work at the intersection of machine learning, large‑scale backend engineering, and business logic, building robust services that blend predictive models with dynamic, engineering logic - all while maintaining extreme performance and reliability requirements.

Job Description

• Own and lead the design and development of low-latency algorithm inference services handling billions of requests per day
• Build and scale robust real‑time decision‑making engines, integrating ML models with business logic under strict SLAs
• Collaborate closely with DS to deploy models seamlessly and reliably in production
• Design systems for model versioning, shadowing, and A/B testing at runtime
• Ensure high availability, scalability, and observability of production systems
• Continuously optimize latency, throughput, and cost‑efficiency using modern tooling and techniques
• Work independently while interfacing with cross‑functional stakeholders from Algo, Infra, Product, Engineering, BA & Business

Requirements

• B.Sc. or M.Sc. in Computer Science, Software Engineering, or a related technical discipline
• 5+ years of experience building high-performance backend or ML inference systems
• Deep expertise in Python and experience with low-latency APIs and real‑time serving frameworks (e.g., FastAPI, Triton Inference Server, TorchServe, BentoML)
• Experience with scalable service architecture, message queues (Kafka, Pub/Sub), and async processing
• Strong understanding of model deployment practices, online/offline feature parity, and real-time monitoring
• Experience in cloud environments (AWS, GCP, or OCI) and container orchestration (Kubernetes)
• Experience working with in-memory and NoSQL databases (e.g. Aerospike, Redis, Bigtable) to support ultra-fast data access in production‑grade ML services
• Familiarity with observability stacks (Prometheus, Grafana, OpenTelemetry) and best practices for alerting and diagnostics
• A strong sense of ownership and the ability to drive solutions end-to-end
• Passion for performance, clean architecture, and impactful systems

Why join us?

• Lead the mission‑critical inference engine that drives our core product
• Join a high-caliber Algo group solving real‑time, large-scale, high-stakes problems
• Work on systems where every millisecond matters, and every decision drives real value
• Enjoy a fast-paced, collaborative, and empowered culture with full ownership of your domain