Senior Forward Deployed Engineer, AI Platform - GP, Remote: Colombia - Costa Ric

- This position is open to candidates located in Colombia or Costa Rica only -

We are looking for a Senior Forward Deployed Engineer to design, build, integrate, and operationalize an enterprise AI Harness that enables teams to safely deploy, orchestrate, govern, observe, evaluate, and scale AI agents, deterministic workflows, automation, and traditional software capabilities across client environments.

This role is ideal for a senior software engineer with deep expertise in at least one engineering discipline and broad experience across APIs, integrations, distributed systems, cloud platforms, and modern application development. Candidates should be comfortable contributing to backend services, platform capabilities, and lightweight frontend experiences when needed.

This is not only an AI application development role. You will build the infrastructure, reusable components, and development patterns that other teams will use to create and operate reliable AI-powered solutions.

What You’ll Do

• Design and build production-grade services, APIs, SDKs, internal tools, and reusable platform capabilities.
• Develop systems that combine AI agents, tools, deterministic workflows, APIs, events, and human approval steps.
• Implement execution capabilities such as agent runtimes, model invocation, reusable skills, backend services, and automated actions.
• Build orchestration patterns involving routing, sequencing, parallel execution, delegation, retries, checkpoints, scheduling, memory, and state management.
• Integrate enterprise context through MCP, RAG, repositories, tickets, documents, databases, search systems, and internal or external APIs.
• Connect the Harness with platforms such as GitHub, Azure DevOps, Jira, Slack, cloud services, SaaS products, and internal applications.
• Implement identity, permissions, policies, approval gates, guardrails, access controls, audit trails, and operational kill switches.
• Build observability capabilities for agent activity, distributed traces, logs, metrics, token consumption, model and tool calls, failures, latency, and cost.
• Create automated evaluations, benchmark datasets, regression suites, quality thresholds, hallucination checks, and model or prompt comparisons.
• Improve developer experience through APIs, SDKs, CLIs, templates, configuration systems, documentation, and reusable reference implementations.
• Build lightweight user interfaces, administrative tools, approval experiences, or operational dashboards when required.
• Deploy and operate solutions across AWS, Azure, or Google Cloud using containers, serverless services, CI/CD, infrastructure as code, IAM, networking, and secrets management.
• Conduct technical discovery in unfamiliar client environments and translate business and technical needs into scalable implementation patterns.
• Move quickly from discovery and experimentation to working integrations and production-ready solutions.
• Communicate architecture decisions, risks, and trade-offs to client engineers, architects, product teams, and technical leadership.

Required Qualifications

• Senior-level experience designing, building, and operating production software systems.
• Deep expertise in at least one area of software engineering, such as backend, full-stack, frontend, platform, cloud, data, or quality engineering.
• Proficiency in one or more programming languages such as Python, TypeScript, JavaScript, Java, Kotlin, C#, or Go.
• Experience building APIs, services, enterprise integrations, or distributed systems.
• Understanding of asynchronous processing, events, state management, scalability, reliability, and architectural trade-offs.
• Experience with REST APIs, GraphQL, webhooks, message queues, databases, and authentication.
• Experience with at least one major cloud platform: AWS, Azure, or Google Cloud.
• Familiarity with containers, serverless computing, CI/CD, IAM, networking, storage, and secrets management.
• Working knowledge of LLM APIs, tool calling, structured outputs, embeddings, RAG, AI agents, and model selection.
• Understanding of when to use agents, deterministic workflows, automation, or traditional software components.
• Experience with SQL, data models, retrieval systems, indexing, or vector stores.
• Ability to troubleshoot systems across applications, infrastructure, APIs, data sources, and external integrations.
• Strong technical discovery, prototyping, problem-solving, and client-facing communication skills.
• Ability to work autonomously in environments with ambiguity and evolving requirements.

Preferred Qualifications

• Experience building AI platforms, internal developer platforms, workflow systems, or enterprise automation solutions.
• Experience with MCP, agent orchestration frameworks, multi-agent systems, or tool integration patterns.
• Experience with Kubernetes, infrastructure as code, distributed tracing, or OpenTelemetry.
• Experience building automated evaluations for AI agents, prompts, models, or retrieval systems.
• Experience with modern frontend frameworks such as React, Angular, or Vue.
• Experience creating SDKs, CLIs, templates, internal tools, or developer documentation.
• Experience working directly with client engineering, architecture, security, or product teams.

Originally posted on Himalayas