Full-Stack AI Engineer

Get to know us better CodiLime is a software and network engineering industry expert and the first-choice service partner for top global networking hardware providers, software providers and telecoms. We create proofs-of-concept, help our clients build new products, nurture existing ones and provide services in production environments. Our clients include both tech startups and big players in various industries and geographic locations (US, Japan, Israel, Europe). While no longer a startup - we have 250+ people on board and have been operating since 2011 we’ve kept our people-oriented culture. Our values are simple: Act to deliver.Disrupt to grow.Team up to win. Renumeration: B2B Contract 16 500 - 28 000 PLN + VAT The project and the team You will work on a large-scale, multi-tenant B2B commercial execution platform used by enterprise go-to-market teams. It combines cloud software, capability benchmarking and advanced analytics to turn commercial strategy into measurable action - from account planning and partner management to pricing and sales performance. This is a hybrid Fullstack + AI Engineering role. You'll turn product and design vision into shipped software, with genuine depth in either front-end UI engineering or backend services, and working competence in the other. Daily use of AI development tools is part of how the whole team works, not an add-on. Beyond building product features, you'll design and integrate generative AI capabilities that connect LLMs with the platform's enterprise data, APIs and internal tools - prompt design, tool calling, workflow orchestration, context management, guardrails and human review - all instrumented so that quality, latency and cost are measurable rather than assumed. You'll be in regular, direct contact with product managers, designers, and client-facing stakeholders, and you'll collaborate with a dedicated team of AI engineers and data scientists on the platform's harder analytical challenges - you own the product integration layer, they own the deeper modeling work. Security runs through everything. This is a multi-tenant SaaS platform handling sensitive enterprise client data, so every feature you ship needs to respect tenant isolation, role-based access control, and least-privilege data access across the UI, API, and AI workflow layers. Technology stack: Frontend: React, TypeScript, MUI / styled-components, ag-Grid, D3.js, amCharts, Mapbox GLBackend: Python (FastAPI) / Node.js, RESTAI: LLM APIs, prompt engineering, tool/function calling, LangChain / LangGraph, RAG, vector search (pgvector, Pinecone) AI-Assisted Development: Claude Code, Codex, or similar AI coding assistantsAI observability: LangSmith, Langfuse, Arize Phoenix, OpenTelemetryData: PostgreSQL, SQL, Snowflake, RedisAuthentication & Security: OAuth 2.0, Okta, JWT, RBACCloud & DevOps: AWS / Azure, Docker, Kubernetes, GitHub ActionsReal-Time & Messaging: Temporal, Socket.IO / WebSockets What else you should know: Team: Product Managers, UX Designers, Fullstack Engineers, Data Engineers, DevOps Engineers, AI Engineers, Data Scientists, client-facing stakeholdersAI-augmented development is a core expectation of the role, not optional - daily use of tools like Claude Code or Codex across coding, testing, debugging, and code reviewMulti-tenant SaaS platform handling sensitive enterprise client data - a security-first mindset is expected across every layerAgile, collaborative, impact-driven environment with close cooperation with business and client-facing stakeholdersStrong ownership culture and product mindsetWe work on multiple interesting projects at a time, so it may happen that we’ll invite you to an interview for another project if we see that your competencies and profile are well suited for it. Your role As a part of the project team, you will be responsible for: Developing features across the full stack, with strong expertise in either React/TypeScript UI or Python (FastAPI)/Node.js services, and working knowledge of the otherWorking with Product Managers and Designers to turn product requirements and designs into production-ready softwareOwning features end to end: from first implementation through release, instrumentation and iteration based on how the feature is actually usedBuilding and integrating generative AI features that connect LLMs with the platform's enterprise data, APIs and internal tools - prompt design, tool calling, workflow orchestration, context management, guardrails and human reviewEvaluating AI workflows and monitoring quality, latency, cost, and failure ratesUsing AI coding assistants effectively while validating all generated output before it reaches production and helping build automated quality gatesParticipating in code reviews, identifying architectural and AI reliability risks, and improving engineering practicesDocumenting data flows, API contracts, and AI workflow behavior clearly enough for non-engineers to act onWriting and optimizing SQL against PostgreSQL and contributing to schema and data-model decisionsApplying security-first thinking at every layer, including tenant isolation, role-based access control, and least-privilege data access across UI, API, and AI workflows Do we have a match? As an AI Engineer, you must meet the following criteria: 6+ years of professional experience in fullstack web developmentStrong experience in either: React / TypeScript UI engineering, or Python (FastAPI) / Node.js backend developmentHands-on experience integrating LLM APIs into production applications, including prompt design, tool/function calling, and safe handling of non-deterministic outputExperience using AI coding assistants such as Claude Code, Codex, or similar on a daily basisStrong SQL and relational database knowledge, preferably PostgreSQLExperience with APIs, authentication, authorization, and technologies such as OAuth 2.0, JWT, and RBACUnderstanding of multi-tenant SaaS application securityExperience with Docker and KubernetesAbility to evaluate AI features and monitor quality, latency, cost, and reliabilityProduct mindset and ownership - you identify problems, propose solutions, and take features from idea to productionStrong communication skills and good knowledge of English (minimum C1 level) Beyond the criteria above, we would appreciate the following nice-to-haves: LLM evaluation and observability tools such as LangSmith, Langfuse, Arize Phoenix, or OpenTelemetryKnowledge of prompt optimization and evaluation techniquesAgentic workflows, multi-step orchestration, guardrails, and human-in-the-loop patternsRAG and vector search, e.g. pgvector or PineconeLangChain or LangGraphExperience with Snowflake or a comparable cloud data warehouseTemporal, Socket.IO / WebSockets, Redis, pub/sub More reasons to join us Flexible working hours and approach to work: fully remotely, in the office or hybridProfessional growth supported by internal training sessions and a training budgetSolid onboarding with a hands-on approach to give you an easy startA great atmosphere among professionals who are passionate about their workThe ability to change the project you work on