warning
Heads-up
Requirements and responsibilities
We're looking for a Senior AI/ML Engineer to design and build the foundational AI layers, multi-step agentic workflows, and developer tooling for the broader engineering organization. You'll focus on the internal runtime for AI: implementing prompt frameworks, enforcing deterministic structured outputs, and deploying production-grade Human-in-the-Loop state automations — turning raw context into reliable, zero-hallucination agent-based actions.RequirementsMust-Have RequirementsOverall Experience: 7+ years in Backend Software Engineering and AI/ML Application EngineeringAgentic Architecture: 2+ years engineering multi-step LLM workflows, autonomous agent loops, and multi-agent orchestration frameworks in productionDeveloper Platform Enablement: experience building internal SDKs, tools, or structured pipeline abstractions used by other product engineering teams to ship AI features rapidlyProficiency in Multi-Step Agentic Workflows & ToolingProficiency in Advanced Amazon Bedrock & Prompt EngineeringProficiency in Structured Output Pipelines & Performance IngestionProficiency in State Management, Automation Consistency & HITLProduction fluency in PythonProficiency in TypeScript/Node.js for Vercel AI SDK and AWS edge workersPreferred ExperienceVercel AI SDK, LangGraph, or LlamaIndex for agentic orchestrationReliable tool-calling (function-calling) interfaces for LLM-driven internal system navigationShort-term and long-term agent memory architectures with ultra-low-latency in-memory stores (Amazon MemoryDB / Redis OSS / Valkey)Amazon Bedrock APIs (foundational model invocation and chaining for agent loops)Programmatic prompt optimization, few-shot prompting, dynamic context injection, and prompt cachingAmazon Bedrock Guardrails (safety gating, prompt injection mitigation, PII redaction)Type-safe schema enforcement with Pydantic (Python) or Zod (TypeScript)Ingestion workers consuming Amazon MSK (Kafka), SQS, and log sourcesOptimistic Concurrency Control (OCC) and async write-delegation to prevent PostgreSQL deadlocksDeterministic multi-step pipelines with AWS Step Functions or LangGraphDurable HITL workflows (pause prior to DB writes or API transactions, persist state, resume on approval)Idempotent execution layers for safe agent loop retries without record duplicationWorking knowledge of C# (.NET Core) or Java for enterprise pipeline integrationsBenefitsRemote work.13 floating holiday.15 vacation days per year completed.Good working environment.
Optionally, you can add more information later (benefits, pre-screening questions, etc.)