AI Engineer

Job description

About the company: United Tech is a global IT product company shaping the future of real-time social connection. With millions of users across North America, Europe, LATAM, and MENA, we build next-gen mobile and web apps for live-streaming and social networking. Our platforms enable connection at scale fast, interactive, and deeply engaging. The market is projected to exceed $206B by 2030, and we are already leading the evolution. Founded in Ukraine, scaling worldwide **About your role:** We’re looking for an AI Engineer who wants to build production-grade AI systems, not just experiment with demos. This is a high-ownership, greenfield role where you’ll help build our AI platform from scratch, working directly with the Head of AI. You’ll own initiatives end-to-end — from discovery and architecture decisions to production delivery — and play a key role in shaping how AI is used across the company. You’ll work with a modern AI stack including Claude/OpenAI/Bedrock, RAG pipelines, eval frameworks (Promptfoo, Ragas, LangSmith), and agentic patterns. This role is ideal for someone who enjoys autonomy, strong engineering ownership, and proactively identifying the next highest-leverage opportunity to drive into production. ### In this role, you will - Design and build RAG and automation workflows inside our VPC environment. - Create integrations across engineering, communication, and knowledge-management systems (Jira, Confluence, Slack, Google Drive, Git). - Develop AI-powered pipelines for code quality checks, ticket auto-classification, documentation updates, release notes, and meeting summaries. - Work on prompt engineering, model selection and routing (Haiku / Sonnet / Opus), and workflow optimization. - Build evaluation and regression frameworks for AI workflows to prevent model-upgrade regressions. - Create lightweight dashboards for engineering leads to surface delivery patterns and bottlenecks. - Own initiatives end-to-end: scope → design → ship → measure → iterate. ### It’s all about you - 5+ years of production experience with Python (services, async, API integrations, clean and testable code). - Hands-on experience with LLM APIs in production: Anthropic Claude (Opus/Sonnet/Haiku), OpenAI, AWS Bedrock. - Strong understanding of RAG systems: chunking, embeddings, hybrid search, re-ranking, grounding/citations. - Prompt engineering + structured outputs + tool/function calling. - Experience with eval/regression frameworks: Promptfoo, Ragas, LangSmith, or custom evaluation harnesses. - Agentic patterns: ReAct, function-calling loops, fallbacks. - Vector databases: pgvector, Pinecone. - Workflow orchestration: n8n, Airflow, or custom orchestration systems. - Observability: token-spend tracing, latency monitoring, model routing. - Solid AWS fundamentals: IAM, Lambda, S3, CloudTrail — comfortable deploying inside VPC environments independently. - CI/CD + pipeline hooks (GitLab/GitHub), webhooks, event-driven architectures. - Basic SQL skills for analytical queries and metrics dashboards. - Driver mindset: proactively identifies the highest-leverage opportunity and drives it to production - B2 English level **Would be a plus** - Real REST integrations with 2–3+ APIs - Experience with workflow orchestration tools. - Prompt evaluation tooling such as LangSmith is nice to have - Experience with Docker - RAG experience: embeddings and vector stores (pgvector, Pinecone, or similar) for knowledge base use cases ### What we offer - 20 paid vacation days, 15 sick days, and 6 additional days off for family events - Up to 10 additional days off for public holidays - 100% medical insurance coverage - Sports and equipment reimbursement - Team building events, corporate gifts, and stylish merch - Financial and legal support - Maternity recovery support allowance - Position retention and support for those who join the Armed Forces of Ukraine - Participation in social initiatives supporting Ukraine - **Comfortable working environment:** - Work from our Kyiv hub or remotely with a flexible schedule - Modern equipment or depreciation of your own tools - **Investment in your future:** - Collaborate with a highly-skilled team of Middle & Senior professionals, sharing practical cases and expertise in the social networking niche - 70% of our heads and leads have grown into their roles here – so can you! - Performance-oriented reviews and Individual Development Plans (IDPs) - Reimbursement for professional courses and English classes - Corporate library, book club, and knowledge-sharing events ### Hiring process - Intro call - Technical Interview - Final Interview - Reference check - Offer