AI Engineer – L3

 

At Robots & Pencils, we build meaningful, scalable digital products by blending strategy, design, and engineering.

We’re looking for an AI Engineer (Level 3) to help build production-ready LLM-powered applications for enterprise clients. You will work hands-on with senior engineers and product teams to implement and scale intelligent systems including RAG pipelines, prompt engineering workflows, document intelligence systems, and evaluation frameworks.

This role focuses on turning working AI concepts into reliable, production-grade systems that deliver real-world impact.

By joining us, you leverage our Advanced AWS Partnership and the highly exclusive AWS Patterns Partnership, a distinction held by only 11 companies worldwide out of 190,000.

 

What You’ll Do

Core AI Pipeline Development

• Build and optimize Retrieval Augmented Generation (RAG) pipelines, including document ingestion, chunking strategies, retrieval, and ranking • Develop document intelligence pipelines for large-scale PDF ingestion, semantic chunking, and structured data extraction

• Implement embeddings-based semantic search and knowledge retrieval capabilities • Design multi-stage LLM workflows where document extraction feeds downstream aggregation or analysis • Develop prompts, guardrails, and structured outputs for domain-specific LLM applications • Implement hallucination mitigation and response validation mechanisms for production systems

Evaluation & Observability

• Support implementation of evaluation frameworks to measure LLM quality, accuracy, and relevance • Build monitoring pipelines for AI system performance and reliability • Analyze evaluation data to refine prompts, retrieval strategies, and system outputs • Debug production AI workflows and continuously improve system behavior

Platform & Backend Integration

• Develop backend services in Python supporting AI workflows and application integration • Integrate vector databases to support semantic search and retrieval • Connect AI systems with external APIs and enterprise data sources • Support scalable and secure deployment of AI features aligned with enterprise architecture

Product Integration & Iteration

• Work closely with product managers, designers, and engineers in cross-functional teams • Integrate AI capabilities into user-facing product experiences • Test AI features with users and iterate based on feedback and performance data • Contribute to agile delivery environments with evolving product requirements

 

Required Skills & Experience

• 4+ years of professional software engineering experience 

• 1–3 years working with applied AI/ML or LLM-powered applications

• Strong experience building backend services using Python

• Experience implementing RAG workflows, prompt engineering, or LLM integrations

• Familiarity with embeddings, semantic search, or vector databases

• Experience integrating APIs or cloud services into production applications

• Understanding of software engineering best practices, testing, and observability

• Ability to work effectively in fast-moving or ambiguous environments

• Bachelor’s degree in Computer Science, Engineering, Data Science, or equivalent experience

 

Nice to Have

• Experience with Azure AI services or OpenAI APIs

• Experience with document processing pipelines (PDF extraction, OCR)

• Experience working with cloud platforms (Azure or AWS) Familiarity with LLM evaluation or monitoring tools such as Langfuse

• Experience contributing to enterprise or B2B software products

 

Tech Stack

LLMs: Claude (Anthropic), Azure OpenAI Backend: Python Vector Databases: Weaviate or similar Infrastructure: Azure or AWS Evaluation & Observability: Langfuse or similar tooling

 

How You Work

Hands-on builder focused on delivering production AI systems • Curious about emerging AI technologies and continuously improving your craft • Comfortable balancing experimentation with reliability • Communicates clearly with cross-functional teams • Thrives in evolving technical environments

 

Why Robots & Pencils

Work on production AI systems delivering measurable client impact • Collaborate with experienced engineers across the full AI lifecycle • Exposure to modern GenAI delivery practices: RAG, evaluation, observability • Work within a globally recognized AWS partner ecosystem