AI Engineer

About the Company

Responsibilities

• ● Design, build, and operate production-grade agentic and GenAI systems-end to end.
• ● Ship services, including robust APIs, reusable components, and secure pipelines that connect LLMs, tools, knowledge, and enterprise systems.
• ● Pair strong software engineering with modern AI practices to deliver measurable business outcomes at scale.
• ● Design multi-agent systems with planning, tool-use, and delegation.
• ● Implement tool adapters with strict type contracts and safe sandboxes.
• ● Build model gateway integrations with routing, rate-limits, retries, and fallback chains.
• ● Stand up RAG services, including chunking, enrichment, embeddings, indexing, and hybrid/vector search.
• ● Implement ingestion pipelines for docs, tickets, chat, and ERP/CRM data, and handle PII redaction and metadata governance.
• ● Optimize retrieval quality with offline/online evaluation and A/B tests.
• ● Treat prompts and graphs as code, and version, diff, and test them.
• ● Build evaluation harnesses and wire into CI.
• ● Add drift detection for conversational systems, and implement safe shutdown and auto-rollback.
• ● Package services as containers, and deploy to Kubernetes with Helm/Argo CD.
• ● Implement policy chains and guardrails, and instrument deep observability.
• ● Manage secrets, signed images, and SBOMs, and enforce least-privilege IAM.
• ● Build tenant isolation and data residency controls, and implement red/blue team prompts and jailbreak defenses.
• ● Ship connectors and events for SAP/CRM/ITSM and Kafka topics, and design idempotent, retry-safe processors.
• ● Automate business workflows with pro-code services first, and expose low-code surfaces only where appropriate.
• ● Partner with Product, Data, and Platform teams to define SLAs/SLOs and success metrics.
• ● Mentor engineers on AI as software practices, and run design reviews and postmortems.

Requirements

• ● 6+ years in software engineering, including 1+ year leading small projects.
• ● Strong in one systems language, and comfortable in a second.
• ● Hands-on with containers, Kubernetes, CI/CD, IaC, and cloud.
• ● Practical LLM experience, including building RAG/agent apps, prompt design, tool-use, and safety patterns.
• ● Data skills, including designing schemas, batch/stream pipelines, and search indexes, and proficiency with SQL and one vector DB.
• ● Testing mindset, including unit/integration tests, load tests, and golden datasets for LLM evals.
• ● Security basics, including secrets, policies, scanning, and least-privilege IAM.