Staff AI Engineer

About the Team

The team is building a shared AI Enablement Platform that enables product teams to ship AI-powered features quickly, safely, and at scale. The platform provides reusable capabilities for building production AI systems, including:

• Reusable APIs for chat, summarization, RAG, classification, and AI workflow execution
• Agent orchestration patterns for multi-step reasoning, tool use, validation, and fallback handling
• Evaluation and validation systems to measure output quality and prevent regressions
• Observability, policy enforcement, cost controls, and production guardrails
• Developer experience, documentation, templates, and reference implementations to accelerate adoption

About the Role

As a Staff AI Engineer – AI Enablement Platform, you will be a core technical builder of the AI platform. This is a deeply hands-on individual contributor role: you will write production code, design and build reusable platform services, review technical designs, debug production issues, and partner with product teams to drive adoption.

You will influence technical direction, establish engineering patterns, and help teams adopt the platform through building real systems. This is not an ML research, data science, or model-training role; it requires a strong platform/backend engineer with production experience in LLM systems, APIs, orchestration layers, evaluation systems, and developer-facing tools.

What You’ll Do

Build the AI platform foundations

• Write and ship production code for AI platform services, APIs, orchestration components, evaluation systems, SDKs, and internal developer tools
• Design, build, and operate reusable capabilities including chat APIs, RAG services, summarization, classification, semantic search, prompt/workflow execution, and agent orchestration
• Build high-quality APIs, SDKs, templates, and reference implementations for product-team adoption
• Create production orchestration patterns for retrieval, tool use, validation, fallback handling, memory/state management, and human-in-the-loop workflows
• Review pull requests, debug production issues, improve reliability, and make pragmatic technical tradeoffs
• Partner with SRE, Security, Platform, and Product Engineering teams to ensure reliability, scalability, security, observability, and cost awareness

Own evaluation, reliability, and production readiness

• Build LLM evaluation harnesses with curated test sets, scenario-based evaluations, regression checks, quality gates, and release criteria
• Implement observability practices including tracing, prompt/version tracking, output-quality monitoring, latency tracking, token/cost visibility, and production feedback loops
• Design safe defaults including structured outputs, tool permissions, prompt-injection awareness, data-handling controls, fallback paths, and failure-mode handling
• Ensure strong production fundamentals: testing, monitoring, rollout strategy, incident readiness, performance tuning, and cost management
• Help teams move from prototypes to production by identifying reliability, observability, security, evaluation, and operational-readiness gaps

Drive AI adoption across the company

• Establish production AI standards through patterns, documentation, code examples, architecture reviews, and technical enablement
• Partner with product teams to adopt the platform, unblock implementation challenges, and build production-ready AI features
• Lead technical design reviews and architecture forums for AI systems
• Convert repeated cross-team friction into reusable platform capabilities
• Raise AI engineering capability through demos, enablement sessions, office hours, technical write-ups, and engineering blog posts

Lead through technical influence

• Act as a hands-on technical leader and multiplier
• Set technical direction for complex AI platform areas and align stakeholders across Product, Engineering, Security, SRE, and Data
• Mentor engineers in production AI engineering, backend design, system reliability, evaluation strategy, and AI-native development workflows
• Help teams use AI-assisted engineering tools responsibly for development, testing, debugging, documentation, and iteration

What This Is Not

• A data science role focused on analysis, experimentation, or dashboards
• An ML research role focused on training foundation models from scratch
• A prompt-only role without production-system ownership
• A role building one-off AI features for a single product line
• An architecture-only role without implementation responsibility
• A people-management role; this is an individual contributor position

What You’ll Need

• Significant hands-on engineering experience, typically 10+ years, with strong backend/platform depth
• Recent experience building and operating production backend/platform systems, including code, APIs, infrastructure, observability, debugging, and production tradeoffs
• Proven delivery of production-grade AI/LLM systems, such as RAG, agent workflows, tool-calling systems, AI APIs, or LLM-powered product capabilities
• Strong programming experience, preferably Python and/or production backend service stacks for APIs and distributed systems
• Deep understanding of API design, service boundaries, SDKs, integration patterns, reliability, testing, observability, performance, and cost optimization
• Practical LLM application architecture experience: context engineering, retrieval, tool use, structured outputs, orchestration, fallback handling, and evaluation
• Ability to build AI evaluation and validation systems using golden datasets, scenario-based tests, regression checks, and quality gates
• Experience deploying and operating cloud production systems on AWS, GCP, Azure, or similar platforms
• Strong technical judgment across speed, reliability, safety, cost, developer experience, and business impact
• Ability to lead through coding, reference implementations, design reviews, mentorship, and delivery of working systems
• Experience influencing across teams through design documents, technical standards, architecture reviews, mentorship, and hands-on partnership

And It’s Great To Have

• Experience building internal developer platforms, SDKs, shared services, or paved-path tooling
• Experience with LLM observability/evaluation tools such as Langfuse, LangSmith, OpenTelemetry-based tracing, or similar tools
• Familiarity with LangChain, LangGraph, LlamaIndex, Semantic Kernel, or custom orchestration frameworks
• Experience with vector databases, embedding workflows, semantic search, retrieval tuning, and RAG productionization
• Experience with AI-native engineering tools such as Cursor, GitHub Copilot, Claude, or ChatGPT
• Experience creating technical blogs, internal engineering guides, architecture documents, or enablement material
• Experience leading technical standards or architecture forums across multiple engineering teams

What Success Looks Like

• Product teams use the AI Enablement Platform as the default starting point for AI-powered features
• Teams move from AI ideas to production features faster through reusable APIs, SDKs, templates, evaluations, and guardrails
• AI systems are observable, measurable, debuggable, and safe to operate in production
• Teams use clear evaluation practices, regression checks, and release gates for LLM-powered workflows
• Repeated AI patterns become shared capabilities rather than one-off implementations
• AI engineering standards are broadly adopted through architecture reviews, documentation, demos, and best practices
• Engineering teams use AI tools and platform capabilities to improve software design, development, testing, review, documentation, and operations

Compensation & What’s Offered

• Compensation range: 420,000 PLN – 450,000 PLN annually (base compensation)
• Eligible employees may receive additional incentive programs where applicable
• Open PTO policy
• Quarterly collective days off globally
• Parental and Pawternity Leave
• Quarterly reimbursement for fitness activities
• Discounts with technology partners
• Medical, dental, and vision coverage, plus an Employee Assistance Program
• Calm App subscription for the employee and up to four dependents