Note: The job is a remote job and is open to candidates in USA. INFUSE is hiring an experienced Senior Full-Stack AI Engineer to develop intelligent AI agents and intuitive user interfaces using a modern, distributed technology stack. The role owns end-to-end feature development across backend services, frontend applications, LLM integrations, databases, observability, testing, and data infrastructure.
Responsibilities
- Backend: deep expertise in Node.js and/or Python (FastAPI); solid grasp of asynchronous programming, RESTful APIs and microservice architectures. LLM integration: production experience building or supporting features on LLM APIs (Anthropic, OpenAI or similar) — structured outputs, retries and rate limits, streaming, fallbacks, and an understanding of token economics. Databases: strong PostgreSQL — query optimisation, execution plans, relational schema troubleshooting, transaction isolation levels. Debugging and observability: practical production troubleshooting with logs, metrics, distributed tracing (trace\_id/request\_id) and monitoring dashboards. Testing: Jest, Supertest or PyTest; robust regression tests; familiarity with evaluating non-deterministic (LLM) behaviour. AI-assisted development: daily fluency with agentic coding tools (Claude Code, Cursor or similar) as a normal working method, including judgement about when AI output needs verification
- LLM observability and evaluation tooling (Langfuse, prompt/trace platforms, eval frameworks). Docker and standard CI/CD pipelines. Queue systems or event-driven architectures (Kafka, RabbitMQ). Security hygiene: dependency vulnerability triage, secrets management
- Analytical, systematic debugging of unfamiliar codebases · systems thinking about how a small config, code or model change hits a broader ecosystem · full ownership from triage to production verification and post-mortem · clear stakeholder communication of root causes · Agile (Scrum/Kanban) with Jira and Confluence
Skills
- Senior, 4–5+ years in product development, with hands-on experience in LLM integration and data engineering
- Deep knowledge of Node.js, Worker threads, and the NestJS ecosystem (solid understanding of Dependency Injection, Modules, Guards, Interceptors, and Pipes)
- Proficient in TypeScript (Vue 3, NestJS) and a proven track record of backend development with Python
- A solid understanding of prompt engineering, LangChain chains, embeddings, and semantic search
- You know exactly how Claude differs from GPT in production environments
- Practical experience with Qdrant (or similar vector databases) — including indexing, similarity search, and vector tuning
- Experience working with distributed systems, message brokers (Kafka), and analytical databases (ClickHouse)
- You clearly understand when to query PostgreSQL, when to aggregate data in ClickHouse (OLAP vs. OLTP), and how vector indexes operate in Qdrant
- Experience with caching (Redis), object storage (S3/MinIO), containerization (Docker/Kubernetes), and the AWS ecosystem
- Strong analytical skills, a product-driven mindset, the ability to architect fault-tolerant systems, and a dedication to writing clean, maintainable code (SOLID, OOP/FP patterns)
Benefits
- Remote working from 14:00 to 23:00 EEST, including a one-hour break.
- Paid vacation and sick leave.
- Opportunities for professional and career growth and development.
- Opportunity to use modern approaches and tools to solve business problems.
Company Overview
Company H1B Sponsorship