AI Engineer

Unico Connect is seeking an AI Engineer to build and ship production AI features for client web and mobile products. The role spans LLM integration, RAG pipeline implementation, evaluation harness setup, and the day-to-day engineering that turns AI proof-of-concepts into reliable production systems. The position is well suited to early-career engineers with hands-on LLM project experience and the appetite to deepen into RAG, agentic workflows, and AI-engineering best practices.

• Build LLM-powered features including chatbots, copilots, RAG search, document AI, and agentic workflows
• Implement RAG pipelines end-to-end covering ingestion, chunking, embeddings, vector indexing, and reranking
• Write Python backends with FastAPI to expose AI capabilities as production APIs
• Set up evaluation pipelines with LangSmith or Ragas to catch behavioural regressions before deployment
• Integrate AI features into React and Next.js client apps with streaming, fallbacks, and rate limiting
• Monitor LLM costs and latency in production; implement caching, model tiering, and prompt compression
• Triage AI-specific incidents including hallucinations, prompt injections, and retrieval poisoning
• Contribute to internal AI engineering documentation, runbooks, and architecture write-ups
• Pair with Senior AI Engineers on architecture decisions and code reviews
• Participate in weekly AI engineering reviews and quarterly evaluation framework retrospectives

• Bachelor's degree in Computer Science, Artificial Intelligence, or a related field
• 1-3 years of software engineering experience with at least 1 production LLM project shipped
• Strong Python (FastAPI or Django) and at least basic Node.js or TypeScript
• Hands-on experience with OpenAI, Anthropic, or Google Gemini APIs
• Familiarity with LangChain or LangGraph, prompt engineering, and embedding-based retrieval
• Working knowledge of vector databases (Pinecone, Weaviate, or pgvector)
• Capacity to write and maintain evaluation harnesses for non-deterministic LLM outputs
• Comfort reading research papers and translating ideas into production code
• Excellent written communication including code comments, ADRs, and incident write-ups
• Working knowledge of REST APIs, async patterns, and PostgreSQL fundamentals

• Fine-tuning experience including LoRA, QLoRA, or full fine-tunes
• Open-source LLM deployment with Llama, Mistral, or Qwen models
• GCP Vertex AI or AWS Bedrock production deployment experience
• Voice AI or computer vision exposure
• Open-source contributions to AI tooling or model libraries

Production engineering at Unico Connect assumes AI tools form part of the daily workflow rather than an experimental augmentation. For this role specifically:

• Claude, ChatGPT, or Cursor as a daily coding driver
• LangSmith or Langfuse for evaluation runs and production trace inspection
• Replicate or Modal for short-cycle model hosting experiments
• Perplexity for AI research and prior-art investigation