Senior Forward Deployed Engineer

Socket.dev; Piscataway Township (NJ); On-site; USD 140,000 - 210,000; Full time

Job summary

Socket.dev is seeking an experienced engineer to design, build, and harden agentic AI applications that integrate with enterprise systems on Microsoft Fabric and Azure AI services.

You will lead a small cross-functional pod, drive rapid prototyping and production delivery, and own security, reliability, and governance of data and write-backs.

The role demands deep cloud know‑how, hands‑on API work, and the ability to translate complex requirements into production‑ready solutions.

Qualifications

• Proven experience building agentic or multi-agent AI systems in production.
• Expertise in state management, concurrency, and authorization for systems acting on records.
• Proficiency in Python, TypeScript/JavaScript, C#, or Java for production code.
• Hands-on integration with enterprise APIs and data platforms.
• Experience with modern AI patterns like retrieval-augmented generation, prompt and context design, and tool use.
• Strong cloud skills, preferably Azure, with end-to-end ownership of apps.
• Ability to prototype rapidly and justify architecture under time pressure.

Responsibilities

• Design, build and harden agentic AI applications that read from and write to enterprise systems of record.
• Embed with a Corporate Function team as the technical lead of a small, multi-functional pod — moving from problem, to prototype, to production at pace.
• Run a tight, iterative build cycle: align on the outcome, prototype, gather feedback, refine and finalise, typically within one to two weeks per loop.
• Own the quality of what you ship end to end — security, reliability, scalability, observability, and safe, governed write-back to source systems.
• Make the right build call for the problem: low-code and agent-builder platforms where they fit, custom code where they do not.
• Ensure the data behind each solution is AI-ready — modelled, governed and documented in Fabric, with lineage and access control that will stand up to audit.
• Set and document the reusable technical patterns, components and guardrails the team applies across every engagement.
• Become credible in a new business domain quickly, and challenge requirements constructively to land on the right solution rather than the requested one.

Skills

Agentic AI systems

State management

Concurrency

Idempotency

Authorization

Python

TypeScript/JavaScript

C#

Java

Enterprise APIs

Data platforms

Azure

Rapid prototyping

Senior IC

Tools

APIs

Data platforms

Job description

WhatYou Will Do

• Design, build and harden agentic AI applications that read from and write to enterprise systems of record, grounded on Microsoft Fabric and Azure AI services.
  
• Embed with a Corporate Function team as the technical lead of a small, multi-functional pod — moving from problem, to prototype, to production at pace.
  
• Run a tight, iterative build cycle: align on the outcome, prototype, gather feedback, refine and finalise, typically within one to two weeks per loop.
  
• Own the quality of what you ship end to end — security, reliability, scalability, observability, and safe, governed write-back to source systems.
  
• Make the right build call for the problem: low-code and agent-builder platforms where they fit, custom code where they do not.
  
• Ensure the data behind each solution is AI-ready — modelled, governed and documented in Fabric, with lineage and access control that will stand up to audit.
  
• Set and document the reusable technical patterns, components and guardrails the team applies across every engagement.
  
• Become credible in a new business domain quickly, and challenge requirements constructively to land on the right solution rather than the requested one.
  

Requirements

RequiredQualifications

• Proven experience building agentic or multi-agent AI systems that run in production and serve real users — working systems, not demonstrations.
  
• Strong command of state management, concurrency, idempotency and authorisation for systems that act on a system of record on behalf of many users.
  
• Substantial software development experience in at least one language such as Python, TypeScript/JavaScript, C# or Java — you can architect, write, review and debug production code.
  
• Hands‑on integration experience with enterprise APIs and data platforms, including designing safe read and write paths and handling failure gracefully.
  
• Working knowledge of modern AI application patterns — retrieval‑augmented generation, prompt and context design, agent orchestration, tool use and protocols such as MCP.
  
• Strong, hands‑on command of a major cloud platform, ideally Azure — able to independently provision, configure, deploy, secure and operate cloud resources, owning an application end to end rather than only consuming pre‑built services.
  
• Demonstrated ability to prototype rapidly, using AI‑assisted development and fast iteration to turn a loosely defined idea into something usable in days.
  
• The judgement and autonomy of a senior individual contributor — able to make sound architecture and feasibility calls alone, under time pressure, and explain them to non‑technical stakeholders.