Senior Forward Deployed Engineer, AI Platform

About the role

This senior position focuses on designing, building, and operationalizing an enterprise AI Harness that enables safe deployment, orchestration, governance, observation, evaluation, and scaling of AI agents, deterministic workflows, automation, and traditional software across client environments. The role blends backend, platform, and occasional lightweight frontend work.

Key responsibilities

• Design and implement 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.
• Build orchestration patterns such as routing, sequencing, parallel execution, retries, checkpoints, scheduling, memory, and state management.
• Integrate enterprise context through repositories, tickets, documents, databases, search systems, and internal or external APIs.
• Connect the Harness with platforms like GitHub, Azure DevOps, Jira, Slack, cloud services, SaaS products, and internal applications.
• Implement identity, permissions, policies, approval gates, guardrails, audit trails, and operational kill switches.
• Create observability for agent activity, distributed traces, logs, metrics, token consumption, model calls, failures, latency, and cost.
• Deploy and operate solutions on AWS, Azure, or Google Cloud using containers, serverless services, CI/CD, IaC, IAM, networking, and secrets management.

Required profile

• Senior‑level experience designing, building, and operating production software systems.
• Deep expertise in at least one engineering discipline (backend, full‑stack, cloud, data, etc.).
• Strong technical discovery, prototyping, problem‑solving, and client‑facing communication skills.
• Ability to work autonomously in ambiguous, evolving environments.

Required skills

• Programming languages: Python, TypeScript, JavaScript, Java, Kotlin, C#, Go.
• API technologies: REST, GraphQL, webhooks, message queues, authentication.
• Cloud platforms: AWS, Azure, Google Cloud; containers, serverless, CI/CD, IAM, networking, storage, secrets management.
• AI/ML knowledge: LLM APIs, tool calling, embeddings, RAG, AI agents, model selection, SQL, vector stores.
• Observability and orchestration: OpenTelemetry, distributed tracing, Kubernetes.
• Frontend frameworks (optional): React, Angular, Vue.