Senior AI Engineer with RAG and Agentic architectures

Job description

We're seeking a Senior AI Engineer to architect and ship LLM-powered applications and agentic systems that address genuine challenges for our users and teams. Your work will span the entire applied-AI stack — from retrieval-augmented generation (RAG) pipelines and prompt design to multi-step agents that reason, leverage tools, and automate end-to-end workflows.

This position is for a senior builder. You'll drive complex use cases from ambiguous problems through to production: selecting appropriate models, implementing agentic architectures, connecting retrieval and tooling, establishing quality evaluation methods, and delivering dependable applications at scale.

Responsibilities

- Architect and deliver production LLM applications — chat, copilots, assistants, and autonomous workflows — from idea to scale

- Construct and implement RAG pipelines: chunking, embeddings, vector search, reranking, and grounding to minimize hallucination and boost relevance

- Create agentic architectures: multi-step reasoning, tool/function calling, planning, memory, and multi-agent orchestration

- Support the automation of business and engineering workflows through agentic AI and workflow automation

- Establish prompt and context strategies; construct evaluation harnesses and maintain quality, latency, and cost standards

- Connect LLMs with internal data, APIs, and tools through connectors, function calling, and structured outputs

- Deploy guardrails, safety, and observability for AI systems (tracing, evals, monitoring for quality and drift)

- Partner with product, data, and platform teams to transform ambiguous problems into shipped AI features

- Exchange knowledge with fellow engineers and take part in design reviews

Requirements

- 3+ years in software or ML engineering, including recent, hands-on experience building and shipping applications with LLMs

- Demonstrated track record of delivering applied-AI systems end to end

- Proficiency in Python at an advanced level

- Background in building RAG systems — embeddings, retrieval, and reranking with vector databases (Pinecone, Qdrant, Milvus, or pgvector)

- Expertise in LLM APIs and orchestration frameworks (OpenAI, Anthropic, LangChain, or LlamaIndex)

- Skills in designing agentic architectures — tool use, function calling, planning loops, and agent orchestration in production

- Competency in automating workflows with agentic AI or workflow-automation tooling

- Knowledge of prompt engineering and structured/JSON output techniques

- Capability to design evaluations and reason about LLM quality, cost, and latency trade-offs at scale

- Strong command of written and spoken English (B2+ level)

Nice to have

- Familiarity with multi-agent frameworks (LangGraph, CrewAI, or AutoGen)

- Background in fine-tuning, adapters (LoRA), or model distillation

- Understanding of MLOps/LLMOps — deployment, versioning, and monitoring of AI systems, including model serving and inference optimization

- Knowledge of AI safety, guardrails, and evaluation frameworks (Ragas, LangSmith, or promptfoo)

- Expertise in cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes)