• Build and extend multi-agent systems and agentic workflows using frameworks such as AWS Agent Core and AWS Bedrock Flows (or equivalent orchestration tools). • Develop and integrate Retrieval-Augmented Generation (RAG) pipelines for internal tools. • Implement LLM-powered chatbots, assistants, and autonomous agents tailored to specific business use cases. • Collaborate closely with the Team Lead to understand requirements and translate them into reliable, scalable implementations. • Take existing proof-of-concept or in-progress AI systems and harden them to production-grade standards. • Pipeline AI components together within the AWS and Databricks ecosystem, ensuring reliable end-to-end data and model workflows. • Apply best practices in observability, logging, and monitoring for deployed AI systems. • Contribute to CI/CD processes for model and prompt deployment where applicable. • Mentor and support other engineers within AI. • Communicate progress, blockers, and technical decisions clearly to both technical and non-technical stakeholders. • Participate in technical discussions and contribute to architectural decisions for AI systems.

Role Description We’re looking for a Senior AI Engineer to design, build, and deliver production AI/ML systems. This role is ideal for an engineer with several years of experience who can confidently own features end-to-end, contribute to architectural decisions, and bring strong technical judgment to the problems they take on. - Design, implement, and deploy ML/AI models end-to-end, from concept through production, including data pipelines, training workflows, and optimization for performance, accuracy, and efficiency. - Maintain and evolve AI systems in production, monitoring for drift, debugging issues, and driving ongoing improvements to reliability and scalability. - Bring an AI-forward coding mindset to your daily work, using tools like Claude and Cursor to ship higher-quality work at pace. - Partner closely with product, engineering, and data teams to align AI work with broader product and business goals. - Translate technical tradeoffs, model behavior, and constraints into terms non-specialists can act on. - Participate actively in code reviews and design discussions, raising concerns and offering constructive feedback. - Contribute to AI architecture decisions with thoughtful perspective on tradeoffs and long-term implications. - Take ownership of meaningful work end-to-end, including the unglamorous parts of getting AI into production. - Raise the bar on engineering practices through your own work and by supporting more junior engineers when opportunities arise. Qualifications - 4+ years professional software engineering experience, with 2+ years focused on AI/ML systems in production and hands-on experience with generative AI development. - Strong software engineering background (Python or similar). - Working knowledge of cloud platforms, preferably with in-depth understanding of AWS services and AWS GenAI offerings. - Proven ability to design and ship agentic systems. - Experience with AI frameworks and orchestration tools. - Experience with evaluation frameworks, and observability tools for LLM apps. - Understanding of AI safety, responsible AI principles, prompt injection defenses, and PII handling. - Hands-on experience building RAG pipelines: chunking strategies, embedding models, vector databases. - API development experience, including designing and integrating with internal and third-party services. - Cost optimization expertise: token economics, caching strategies, model routing, quantization. - Working knowledge of Docker and Kubernetes for containerized deployments. - Demonstrable, day-to-day usage and knowledge of AI-forward coding tools such as Claude Code and Cursor. - Strong problem-solving skills and the ability to navigate ambiguous technical challenges with sound judgment. Requirements - A doer who sees something broken and fixes it. - A fast learner who is curious and keeps learning. - Direct in a way that improves work quality. - Obsessed with craft and detail. - Built for ownership and accountability. - All in for client success and resourceful under constraints. - Glad to collaborate with experienced team members. Benefits - Comprehensive package of benefits including paid time off. - Medical/dental/vision insurance. - 401(k) to eligible employees. Company Description Robots & Pencils is an applied AI engineering firm building the next frontier of business architecture. We design and ship AI co-workers that integrate into enterprise operations and deliver measurable results for our clients. Founded in 2009, we are smaller, faster, and more senior by design, with teams averaging 15+ years of experience.

Role Description Own the design and operation of internal automations and AI-powered agents. You’ll turn API workflows into reliable, observable systems using n8n and LLMs. Key Responsibilities: - Build and maintain n8n workflows and custom nodes that orchestrate APIs, webhooks, and LLM calls. - Design AI-assisted flows (classification, extraction, summarization, decision support) with clear guardrails. - Implement secrets management, RBAC, rate limiting, and prompt-injection defenses. - Add monitoring, alerting, and cost tracking; set SLOs for critical automations. - Write concise docs/playbooks; enable self-serve patterns for teammates. - Continuously improve reliability, latency, and cost via testing and iteration. - Strong hands-on with n8n (or Make/Zapier/Airflow) and REST/GraphQL APIs. - Proficiency in Python or other programming languages for custom logic/integrations. - Practical LLM experience (function calling, prompting, evaluation basics). - Solid grasp of auth (OAuth2/JWT), webhooks, queues, retries, and idempotency. - SQL fundamentals and basic NoSQL familiarity. - Security mindset: data handling, secrets, dependency hygiene. Qualifications - Strong hands-on with n8n (or Make/Zapier/Airflow) and REST/GraphQL APIs. - Proficiency in Python or other programming languages for custom logic/integrations. - Practical LLM experience (function calling, prompting, evaluation basics). - Solid grasp of auth (OAuth2/JWT), webhooks, queues, retries, and idempotency. - SQL fundamentals and basic NoSQL familiarity. - Security mindset: data handling, secrets, dependency hygiene. Requirements - GCP/AWS, Docker/Kubernetes, GitOps/CI. - Observability (logs/metrics/traces). - Exposure to LangChain or RPA/BPM concepts.

• Advanced Prompt Engineering: Designing complex, dynamic prompt templates with conditional logic and efficiently reusing information and context within prompts to maximize generation quality and reasoning. • Structured Outputs & Schemas: Implementing various response schemes (JSON mode, function calling, Zod/JSON schemas) to ensure AI outputs are predictable and ready for seamless integration into application logic. • Prompt Engineering & Evaluations: Building robust evaluation pipelines and using Langfuse to collect feedback and score the quality of responses in real time. • Tracing & Debugging: Performing deep debugging of complex LLM chains using Langfuse traces to identify bottlenecks and optimize for cost, latency, and context window usage. • AI A/B Testing: Running systematic experiments across different models via OpenRouter (e.g., comparing Claude 3.5 Sonnet vs. GPT-4o) and analyzing results based on quantitative metrics. • Data-Driven Decisions: Making deployment decisions for new prompts or models strictly based on quantitative benchmarks and trace data, rather than intuition. • Output Scoring & Analysis: Developing scoring systems to analyze the “Problem → Solution” chain and identify root causes of hallucinations or logic errors using Langfuse analytics. • Model Performance & Fine-Tuning: Regularly re-evaluating model performance as new architectures emerge and performing fine-tuning when necessary to meet specific domain requirements.