Artificial Intelligence Engineer ID42044

• What you will do

• Build AI applications: Design and deploy intelligent systems that parse tariffs, optimize utility spend, and automate workflows—shipping production-grade features quickly while maintaining quality.
• Document-centric RAG with OpenAI: Implement RAG using structured tool/JSON outputs, streaming and batch flows, with robust guardrails, red-teaming, and RAG evaluation (e.g., RAGAS, TruLens).
• Productionize agent workflows: Integrate cutting-edge AI models into resilient pipelines and services that run reliably in real-world environments.
• Scraping/ingestion at scale: Create pipelines for automated utility logins → parse/store bills & usage → anomaly detection → “ready-to-audit” bills, with full auditability and data lineage.
• Production services on cloud: Build and operate on GCP (Cloud Run and/or GKE); use BigQuery as the analytics backbone feeding Looker; leverage Firestore for app state and permissions. (AWS experience transferable.)
• APIs & full-stack delivery: Develop APIs and backend services in Python/TypeScript and collaborate with frontend integrations as needed.
• Reliability, cost & latency controls: Lead feature-flagged rollouts, implement end-to-end tracing, and enforce p95/p99 SLOs, budgets, and rate-limiting to balance performance and spend.
• Iterate rapidly: Prototype, test, and launch features fast; harden successful prototypes into scalable, observable, secure services.
• Shape foundations: Establish engineering standards, architecture principles, and AI-first practices that set the bar for the company.

• Must haves

• Experience level: 4+ years as a software engineer and at least 2+ years at an AI-first company or building AI-powered applications.
• Production engineering: Professional experience building and maintaining APIs, data pipelines, or full-stack applications in Python and TypeScript.
• LLM workflow deployment: Hands-on deploying AI/LLM workflows to production (e.g., LangChain, LlamaIndex, orchestration frameworks, vector databases).
• Startup DNA: Thrives in ambiguity, bias to action, problem-first mindset, and high ownership.
• RAG in production: Proven track record shipping document-centric RAG (retrieval, chunking, embeddings/vector DBs, re-ranking) with OpenAI, structured tool/JSON outputs, and streaming responses.
• RAG evaluation: Hands-on use of RAGAS and/or TruLens (faithfulness, answer relevance, context precision/recall) with measurable quality gates.
• Guardrails & safety: JSON Schema/Pydantic validation, moderation and grounding checks, plus red-teaming practices in production.
• Cloud production (GCP-first): Experience operating services on Cloud Run/GKE, using BigQuery (consumed in Looker) and Firestore for app state/permissions; strong CI/CD discipline. (AWS familiarity is a plus/transferable.)
• Scraping/ingestion at scale: Built and operated pipelines with authentication (e.g., multi-tenant logins), robust parsing/storage, and audit-ready artifacts (data lineage, repeatability).
• Observability & controls: Structured logging, tracing (e.g., OpenTelemetry), metrics; cost/latency guardrails and safe releases (feature flags, canary, rollback) meeting p95/p99 SLOs.
• English: Upper-Intermediate English level.

• Nice to haves

• Experience with parsing unstructured data, optimization algorithms, or time-series forecasting.
• Background in energy, utilities, or IoT data (not required, but valuable context).
• Prior experience in a founding or early-stage engineering role.
• Vector databases (pgvector, Pinecone, Weaviate) and re-ranking experience.
• GCP IaC (Terraform), Secrets/IAM hardening; Looker/LookML modeling.

AgileEngine is an Inc. 5000 company that creates award-winning software for Fortune 500 brands and trailblazing startups across 17+ industries. We rank among the leaders in areas like application development and AI/ML, and our people-first culture has earned us multiple Best Place to Work awards.

If you’re looking for a place to grow, make an impact, and work with people who care, we’d love to meet you! 🙂