Job VC
Senior AI Platform Engineer
Technologies
Description
We are looking for a
Senior AI Platform Engineer
to join our team at
ORIL
. This is an opportunity to work on a high-stakes AI-driven platform where performance, reliability, and data integrity are at the core of everything we build. If you thrive in a fast-paced startup environment, take full ownership of your systems, and have a "ship-fast-but-stable" mindset, we want to talk to you.
About the project
Our client is a US-based innovator pushing the boundaries of AI workflows. We are building sophisticated, multi-step AI systems that require deep observability, robust data pipelines, and a seamless CI/CD process to maintain high velocity without sacrificing quality.
Tech Stack:
Python, AI/LLM Orchestration, Distributed Tracing, AWS, PostgreSQL, Modern CI/CD.
What are we looking for?
4+ years of experience building and owning production-grade backend systems in Python;
Recent experience instrumenting distributed tracing or node-level observability for multi-step AI workflows to diagnose complex bottlenecks;
Proven ownership of end-to-end data pipelines: from ingestion and embedding to retrieval validation and schema enforcement;
Hands-on experience setting up CI/CD gates that run evals, schema validation, or integration tests automatically before a merge;
High shipping velocity: track record of shipping 5+ pull requests in a single day on a production codebase, each closing a distinct issue;
Latency Optimization: experience profiling and fixing bottlenecks in Python backends (P95 < 1.5s) for real-time or near-real-time requests;
System Responsibility: experience owning systems with a high "blast radius" where other engineers depend on your changes daily;
Experience writing deployment SOPs or runbooks that allow others to execute deployments without direct involvement;
Technical Stack: Proficient in LangGraph (state machines, node composition), PostgreSQL (pgvector), and RAG pipelines;
English level: Upper-Intermediate (B2+).
What will you do?
Develop and maintain multi-step AI workflows and the infrastructure that supports them;
Set up and improve CI/CD gates that run integration tests and schema validations automatically before every merge;
Maintain a high shipping tempo (handling multiple PRs daily) while keeping the codebase clean;
Write deployment SOPs and runbooks to ensure system stability and team autonomy;
Diagnose and fix complex issues in distributed systems using advanced tracing tools;
Work closely with the engineering team to refine the technical roadmap and ensure architectural consistency.
We offer:
Competitive compensation;
Flexibility to work from anywhere (fully remotely or in our office in Lviv);
Accounting Support Services;
Education budget + corporate education events/trainings;
Compensation for certifications, fitness, or therapy sessions;
A dynamic environment where your proactivity is recognized and rewarded.
Application Process:
Initial Screening:
Call with Recruiter.
Technical Interview:
Be ready to share specific examples of diagnosing bottlenecks and managing data pipelines.
Client Interview.
Ready to build the future of AI infrastructure? Apply now and let’s get to work!
Senior AI Platform Engineer
to join our team at
ORIL
. This is an opportunity to work on a high-stakes AI-driven platform where performance, reliability, and data integrity are at the core of everything we build. If you thrive in a fast-paced startup environment, take full ownership of your systems, and have a "ship-fast-but-stable" mindset, we want to talk to you.
About the project
Our client is a US-based innovator pushing the boundaries of AI workflows. We are building sophisticated, multi-step AI systems that require deep observability, robust data pipelines, and a seamless CI/CD process to maintain high velocity without sacrificing quality.
Tech Stack:
Python, AI/LLM Orchestration, Distributed Tracing, AWS, PostgreSQL, Modern CI/CD.
What are we looking for?
4+ years of experience building and owning production-grade backend systems in Python;
Recent experience instrumenting distributed tracing or node-level observability for multi-step AI workflows to diagnose complex bottlenecks;
Proven ownership of end-to-end data pipelines: from ingestion and embedding to retrieval validation and schema enforcement;
Hands-on experience setting up CI/CD gates that run evals, schema validation, or integration tests automatically before a merge;
High shipping velocity: track record of shipping 5+ pull requests in a single day on a production codebase, each closing a distinct issue;
Latency Optimization: experience profiling and fixing bottlenecks in Python backends (P95 < 1.5s) for real-time or near-real-time requests;
System Responsibility: experience owning systems with a high "blast radius" where other engineers depend on your changes daily;
Experience writing deployment SOPs or runbooks that allow others to execute deployments without direct involvement;
Technical Stack: Proficient in LangGraph (state machines, node composition), PostgreSQL (pgvector), and RAG pipelines;
English level: Upper-Intermediate (B2+).
What will you do?
Develop and maintain multi-step AI workflows and the infrastructure that supports them;
Set up and improve CI/CD gates that run integration tests and schema validations automatically before every merge;
Maintain a high shipping tempo (handling multiple PRs daily) while keeping the codebase clean;
Write deployment SOPs and runbooks to ensure system stability and team autonomy;
Diagnose and fix complex issues in distributed systems using advanced tracing tools;
Work closely with the engineering team to refine the technical roadmap and ensure architectural consistency.
We offer:
Competitive compensation;
Flexibility to work from anywhere (fully remotely or in our office in Lviv);
Accounting Support Services;
Education budget + corporate education events/trainings;
Compensation for certifications, fitness, or therapy sessions;
A dynamic environment where your proactivity is recognized and rewarded.
Application Process:
Initial Screening:
Call with Recruiter.
Technical Interview:
Be ready to share specific examples of diagnosing bottlenecks and managing data pipelines.
Client Interview.
Ready to build the future of AI infrastructure? Apply now and let’s get to work!