AI Platform Engineer

We are looking for a Senior AI Platform Engineer to build and own our company-wide AI platform from the ground up - a reliable, secure, and cost-transparent foundation that empowers every team to leverage LLMs and delegate work to autonomous AI agents. In this role, you will take full ownership of the platform’s core architecture and drive internal adoption across the entire company. You will lead the delivery of our internal LLM gateway as the single entry point for all model providers - complete with team quotas, cost tracking, and automated failovers - while establishing an observable shared platform with monitoring and alerting. In parallel, you will ship native internal SDKs for our primary tech stacks, deploy an Agent Control Plane enabling teams to orchestrate and track autonomous workflows, and partner directly with internal squads to turn high-impact business use cases into production-grade solutions.

Responsibilities

• Architect, build, and operate the internal LLM Gateway, including routing, rate limiting, quotas, cost tracking, and automated fallbacks.
• Design and build the agent control plane, covering agent creation, context management, task execution, and state tracking.
• Build and maintain internal SDKs to simplify LLM integration across teams.
• Implement platform observability, monitoring, alerting, tracing, and evaluation of LLM and agent workflows, including latency, token usage, costs, and failovers.
• Implement security and governance for LLM usage and AI agents.
• Collaborate with internal teams to translate business needs into working AI solutions and drive AI adoption.
• Evaluate build-vs-buy options and integrate relevant open-source tools where appropriate.

Requirements

• 5+ years of experience in backend development.
• Strong proficiency in Python or another modern backend language (Go, TypeScript, Rust), with a willingness to work with Python as our primary platform language.
• Deep understanding of distributed systems (async queues, rate limiting, retries, circuit breakers, failover mechanics).
• At least 1 year of hands-on experience working with AI/LLM-based solutions.
• Practical experience with LLM APIs (OpenAI, Anthropic, Gemini): streaming, tool calling, context management, and rate limits.
• Hands-on experience building AI agents or agentic workflows.
• Solid knowledge of observability (metrics, logs, tracing), 
• Experience with Docker, Kubernetes, and Cloud (AWS or GCP).
• Strong logical thinking, high ownership, initiative, and product mindset.
• English - Intermediate or higher.
• Ukrainian - Advanced.

Will be a plus

• Experience building developer platforms, internal tooling, API Gateways, or SDKs.
• Hands-on experience with MCP (Model Context Protocol), RAG pipelines, or vector databases.
• Experience with LLM observability and evals tools (Langfuse, LangSmith, OpenTelemetry).
• Active personal AI adoption (demonstrated use of AI tools/agents to automate own workflows).
• Degree in Computer Science, Software Engineering, or a related field.

We offer

• 20 paid vacation days per year
• 10 paid sick leave days per year
• Public holidays as per the company’s approved Public holiday list
• Medical insurance
• Opportunity to work remotely
• Professional education budget
• Language learning budget
• Wellness budget (gym membership, sports gear and related expenses)

Role mission

Build and own the company’s internal AI platform: a reliable, secure and cost-transparent foundation that lets every team use LLMs and delegate work to AI agents, accelerating AI adoption across сompany.

Requirements hard skills

[5+] years of backend development of production services.
Strong [Python / Go / TypeScript / Rust] (at leash one of these).
Distributed systems: async task processing, queues, retries, rate limiting, failover.
Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini or similar): tool calling, context management, streaming, error and limit handling.
Practical experience building AI agents or agentic workflows.
Observability: metrics, logs, tracing.
Cloud and infrastructure: [AWS / GCP], Docker, [Kubernetes].
Security basics: access control, secrets management.

Requirements soft skills

High ownership: able to take a broad, loosely defined area and drive it to results independently.
Product mindset: treats internal teams as customers, collects feedback, prioritizes by value.
Clear communication with both engineers and non-technical stakeholders.
Pragmatism in build-vs-buy decisions.
Curiosity and fast learning in a quickly changing AI landscape.
Proactiveness in promoting AI adoption.

Responsibilities

Design and build the agent control plane: agent creation, context management, task execution and tracking.
Build and operate the LLM gateway: routing, quotas, usage and cost tracking per team, fallbacks.
Develop and support the shared LLM platform with monitoring and alerting.
Create and maintain internal SDKs for different teams.
Implement security and governance for LLM usage and agents.
Set up tracing and evaluation of agent runs.
Evaluate and integrate existing tools where it makes sense.
Consult teams on AI use cases and help them adopt the platform.

Will be a plus

Experience building developer platforms, API gateways or internal SDKs.
MCP, RAG pipelines, vector databases.
LLM evals and agent observability tools (Langfuse, LangSmith, OpenTelemetry).
Ability to build a simple internal UI when needed.
Bachelor’s degree in CS or related field.