Senior Applied AI Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Lead small engineering teams in the design, development, and delivery of complex, high-impact AI projects.

• Take ownership of the technical execution from the initial design phase through implementation, testing, deployment, and ongoing operations.

• Transform vague product requirements into concrete technical strategies, engineering tasks, and delivery milestones.

• Facilitate architectural discussions, assess trade-offs, and define implementation strategies.

• Coordinate engineering activities, identify dependencies and obstacles, and ensure accountability for successful delivery.

• Contribute to production code and tackle challenging technical issues alongside the team.

• Collaborate with Product and Engineering leadership, as well as stakeholders, to achieve impactful business outcomes.

• Design, construct, and maintain production-grade AI systems utilizing LLMs, agentic workflows, retrieval architectures, and backend services.

• Develop agent workflows featuring tool calling, structured outputs, multi-step reasoning, deterministic validation, and human-in-the-loop controls.

• Build and optimize RAG systems, which include ingestion pipelines, embeddings, semantic retrieval, and context assembly.

• Integrate foundational models via Amazon Bedrock and AWS AgentCore.

• Create AI evaluation frameworks encompassing regression testing, golden datasets, trace analysis, and quality measurement.

• Enhance AI systems for reliability, accuracy, latency, observability, and cost efficiency.

• Design systems capable of handling unpredictable model behaviors, edge cases, operational failures, and production constraints.

• Raise engineering standards through code reviews, architectural guidance, mentorship, and technical leadership.

• Mentor engineers in software design, debugging, testing, system architecture, and production engineering practices.

• Establish best practices regarding code quality, automated testing, documentation, maintainability, and operational readiness.

• Enhance engineers' technical judgment, ownership, independence, and problem-solving skills.

⛳️ Requirements

• Must be a US citizen or authorized to work in the United States.

• Minimum of 7 years of professional software engineering experience.

• Strong expertise in Python and modern backend software engineering.

• Proven experience in designing and delivering production systems.

• Experience in technical leadership roles for engineering projects or small teams, encompassing architecture, implementation, mentorship, and delivery.

• Hands-on experience in designing, building, and deploying production AI applications using LLMs, agentic workflows, retrieval systems, or similar technologies.

• In-depth knowledge of backend architecture, APIs, distributed systems, databases, and workflow orchestration.

• Experience in designing agentic workflows, tool-calling systems, structured outputs, or retrieval-augmented generation architectures.

• Familiarity with production AI challenges, including model reliability, hallucination mitigation, evaluation, observability, latency, and cost management.

• Experience with automated testing, code reviews, CI/CD, system design, and maintainability.

• Familiarity with cloud infrastructure, preferably AWS.

• Ability to mentor engineers, provide constructive technical feedback, and influence engineering practices.

• Strong technical judgment and debugging capabilities.

• Skill in navigating complex systems and ambiguous requirements.

• Ability to balance hands-on engineering contributions with technical leadership duties.

• Excellent communication and collaboration skills across engineering, product, and business teams.

• Experience working in fast-paced environments where ownership, adaptability, and execution are critical.

• Preferred: Experience with Amazon Bedrock, AWS AgentCore, Lambda, Step Functions, S3, DynamoDB, RDS, SQS, or related AWS services.

• Preferred: Experience with LangGraph, LangChain, DSPy, Semantic Kernel, or similar agent orchestration frameworks.

• Preferred: Experience in building multi-step autonomous agents that interact with tools, APIs, external systems, or business workflows.

• Preferred: Experience in developing AI evaluation frameworks, prompt regression testing, trace analysis, or human-in-the-loop review systems.

• Preferred: Familiarity with vector databases and semantic retrieval technologies such as OpenSearch, pgvector, Pinecone, Weaviate, or FAISS.

• Preferred: Experience with LLM observability and evaluation platforms like LangSmith, Arize, Helicone, Weights & Biases, or OpenTelemetry.

• Preferred: Experience leading technical initiatives within startup or rapidly growing SaaS organizations.

• Preferred: Experience in improving engineering practices and enhancing technical maturity.

🏝️ Benefits

• Fully remote work arrangement.

• Opportunity to engage in high-impact AI initiatives.

• Opportunities for technical leadership and mentorship.

• Involvement in the development of advanced AI capabilities and production-grade systems.