AI/ML Engineer – Agentic Workflows

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

📋 Description

• Create and develop the essential AI components for the larger engineering team.

• Establish prompt frameworks and ensure deterministic structured outputs.

• Implement production-grade Human-in-the-Loop state automations.

• Convert raw context into dependable, zero-hallucination actions driven by agents.

⛳️ Requirements

• Overall Experience: 7+ years in Backend Software Engineering and AI/ML Application Engineering.

• Agentic Architecture: 2+ years of experience in engineering multi-step LLM workflows, autonomous agent loops, and multi-agent orchestration frameworks in a production environment.

• Developer Platform Enablement: experience in creating internal SDKs, tools, or structured pipeline abstractions utilized by other product engineering teams to rapidly deliver AI features.

• Proficiency in Multi-Step Agentic Workflows & Tooling.

• Proficiency in Advanced Amazon Bedrock & Prompt Engineering.

• Proficiency in Structured Output Pipelines & Performance Ingestion.

• Proficiency in State Management, Automation Consistency & HITL.

• Production fluency in Python.

• Proficiency in TypeScript/Node.js for Vercel AI SDK and AWS edge workers.

• Familiarity with Vercel AI SDK, LangGraph, or LlamaIndex for agentic orchestration.

• Reliable tool-calling (function-calling) interfaces for LLM-driven internal system navigation.

• Experience with short-term and long-term agent memory architectures featuring ultra-low-latency in-memory stores (Amazon MemoryDB / Redis OSS / Valkey).

• Knowledge of Amazon Bedrock APIs (foundational model invocation and chaining for agent loops).

• Expertise in programmatic prompt optimization, few-shot prompting, dynamic context injection, and prompt caching.

• Understanding of Amazon Bedrock Guardrails (safety gating, prompt injection mitigation, PII redaction).

• Type-safe schema enforcement using Pydantic (Python) or Zod (TypeScript).

• Experience with ingestion workers consuming Amazon MSK (Kafka), SQS, and log sources.

• Familiarity with Optimistic Concurrency Control (OCC) and async write-delegation to prevent PostgreSQL deadlocks.

• Ability to design deterministic multi-step pipelines utilizing AWS Step Functions or LangGraph.

• Experience in creating durable HITL workflows (pausing before DB writes or API transactions, persisting state, and resuming upon approval).

• Knowledge of idempotent execution layers for secure agent loop retries without record duplication.

• Working knowledge of C# (.NET Core) or Java for enterprise pipeline integrations.

🏝️ Benefits

• Remote work.

• 13 floating holidays.

• 15 vacation days per year upon completion.

• A positive working environment.