AI Automation Engineer (Python & LLM)

• Design, build, and operate AI-powered automations to eliminate manual effort in business and engineering workflows.
• Build and deploy end-to-end AI automations and agentic workflows integrating LLMs with internal systems, APIs, and data sources.
• Design and implement retrieval-augmented generation (RAG) pipelines including chunking, embedding, vector search, re-ranking, and grounded response generation.
• Develop tool- and function-calling integrations for agents to act on systems of record.
• Partner with business stakeholders to map processes, quantify manual effort, and prioritize automation backlog.
• Write production Python services and jobs with logging, retries, and error handling.
• Build prompt and model evaluation harnesses including golden datasets, regression tests, and quality gates.
• Instrument automations with observability and tracing for early detection of failures and quality drift.
• Implement human-in-the-loop checkpoints and approval steps where full autonomy is inappropriate.
• Optimize for cost and latency through model selection, caching, batching, and prompt compression.
• Document architecture, runbooks, and handover material; support and iterate on automations post-launch.
• Follow security, privacy, and responsible AI requirements around data handling and model usage.

Requirements

Must-Have:

• 3-5 years of professional software, data, or automation engineering experience, including at least 1 year building with LLMs or AI services.
• Strong Python skills including async programming, API integration, testing, and clean code.
• Practical experience with LLM APIs (Anthropic Claude, OpenAI, Gemini, Bedrock) in real applications.
• Hands-on experience with at least one agent or orchestration framework (LangChain, LangGraph, Llamalndex, CrewAI, Semantic Kernel, AutoGen, or equivalent).
• Experience building RAG systems and working with vector stores (pgvector, Pinecone, Weaviate, Qdrant, Milvus, OpenSearch, or similar).
• Solid grasp of prompt engineering, context design, and structured output techniques.
• Familiarity with Model Context Protocol (MCP) and building MCP servers.
• Strong REST/GraphQL API integration skills including OAuth, token-based authentication, webhooks, pagination, and rate-limit handling.
• Working knowledge of SQL and data modeling.
• Experience with Git workflows, code review, and CI/CD.
• Cloud experience on AWS, Azure, or GCP including compute, serverless functions, queues, secrets management, and managed AI services.
• Containerization fundamentals with Docker.
• Proven ability to work directly with stakeholders for requirements elicitation, demos, and expectation management.

Nice-to-Have:

• Experience with workflow automation platforms (n8n, Zapier, Power Automate, Airflow, Temporal, Prefect, Dagster).
• Background in RPA (UiPath, Automation Anywhere, Blue Prism) and modernizing RPA automations with AI.
• Experience with LLM observability and evaluation tooling (LangSmith, LangFuse, Arize, Braintrust, Ragas, DeepEval).
• Multi-agent system design including planner/executor patterns and supervisor architectures.
• Document intelligence and multimodal work (OCR, PDF parsing, table extraction, vision models).
• Frontend familiarity (React.js, Next.js, TypeScript) for internal tools and demos.
• Infrastructure-as-code (Terraform, CloudFormation) and Kubernetes exposure.
• Experience with enterprise governance concerns including AI risk review, audit trails, data residency, and access-scoped retrieval.
• Bachelor's degree in Computer Science, Engineering, or related field, or equivalent experience.