Role overview
- Lead the design, development, and deployment of AI-powered services and product features into production.
- Design and build scalable and reliable backend infrastructure to support AI capabilities (APIs, workflows, guardrails, monitoring, cost controls).
- Own the lifecycle of AI services end-to-end: discovery, prototyping, evaluation, production rollout, monitoring, iteration, and maintenance.
- Contribute to building RIVO’s AI foundation by developing reusable building blocks (shared libraries, templates, integration patterns, evaluation utilities).
- Apply advanced prompt engineering techniques and LLM orchestration patterns (tool/function calling, structured outputs, routing, fallback strategies) to achieve reliable and predictable behavior.
- Implement and optimize retrieval-based systems including embeddings, vector search, and RAG pipelines.
- Research, evaluate, and recommend models, tools, and frameworks, balancing quality, latency, cost, and maintainability.
- Write high-quality, production-ready code and actively participate in code reviews and architectural discussions.
What we're looking for
Knowledge and Experience**
- 7+ years of software development experience, with at least 3 years focused on AI/LLM-based applications.
- Proven experience delivering AI capabilities into production environments and maintaining them over time.
- Deep understanding of LLMs and their practical application to real-world problems (e.g., OpenAI, Anthropic, Mistral, open-source).
- Extensive experience with Python and/or Node.js for backend development in distributed systems.
- Strong grasp of prompt design, embeddings, and AI API orchestration.
- Experience with evaluating AI systems (offline evaluation, regression tests, monitoring, analytics).
- Experience working with cloud providers (AWS preferred) and modern engineering tools (CI/CD, containerization, infrastructure-as-code).
- Familiarity with vector databases (pgvector, Pinecone, Weaviate, Qdrant, OpenSearch).
- Solid understanding of RAG pipelines, reranking, hybrid retrieval techniques, and optimization strategies.
- Experience integrating open-source models or model-serving approaches (e.g., vLLM, llama.cpp, quantization, self-hosting).
Skills
- Strong ownership and accountability, comfortable delivering independently and driving tasks to completion.
- Ability to operate in a global, multi-cultural environment and collaborate across time zones.
- Strong organizational and time management skills.
- Ability to prioritize tasks effectively and balance speed with quality.
- Strong work ethic, proactive, self-motivated, and results-driven.
- Excellent communication and collaboration skills.
- Proficient in spoken and written English
Tags & focus areas
Used for matching and alerts on DevFound Ai Ai Engineer