AI Deployment Engineer

Job Description This role is responsible for the technical implementation of agents and workflows on Medable's Agent Studio platform. The primary work is full-stack engineering: building and maintaining server-side applications, databases, API integrations, and front-end interfaces that support agentic clinical deployments. The engineer also executes acceptance testing, maintains build documentation, and provides structured product feedback before any agent hands off to a Forward Deployed Engineer (FDE). Core Responsibilities Engineering & Build

• Build and maintain full-stack infrastructure supporting Agent Studio deployments: React, Node.js, REST APIs, Postgres, Docker.
• Configure workflow orchestration, task routing logic, Human-in-the-Loop (HITL) escalation gates, and confidence scoring thresholds.
• Use AI-native engineering tools and workflows — Claude Code, Cursor, Model Context Protocol (MCP) integrations — as standard practice.
• Set up and test MCP connector integrations with clinical systems: Electronic Data Capture (EDC), Clinical Trial Management System (CTMS), electronic Trial Master File (eTMF), and sponsor-specific tools.
• Write and refine agent prompts to Medable's context engineering standards: precise, functional, and Good Practice (GxP)-defensible.
• Identify reusable patterns across builds and contribute documented components to the shared pattern library. Quality & Documentation
• Execute acceptance testing against Medable's formal quality standards before FDE handoff.
• Document test results, log failures with root causes, and iterate until pass criteria are met.
• Systematically evaluate and debug AI outputs and workflows: identify whether failures stem from model behavior, prompt design, integration issues, or configuration gaps before escalating or iterating.
• Build and maintain a standard helpdesk subagent for each deployed clinical agent.
• Maintain build documentation clear enough for another engineer to pick up or configure the agent in a new environment. Product Feedback
• Capture where Agent Studio creates friction, where platform capabilities fall short, and where gaps limit reusability.
• Submit structured product feedback to the Agent Studio & Services team. Surface gaps with specifics, not anecdotes. Scope & Decision Rights
• Owns technical implementation, quality gates, and documentation for all assigned agents and workflows on Agent Studio.
• Has decision authority over Agent Studio configuration, prompt design, and workflow orchestration within approved, developer-ready specifications.
• Accountable for acceptance testing before FDE handoff.
• Provides structured product feedback that directly informs the Agent Studio platform roadmap.

Pay Ranges from $20/hr-$30/hr We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment regardless of their race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or recruiting process, please send a request to HR@insightglobal.com.

To learn more about how we collect, keep, and process your private information, please review

Insight Global's Workforce Privacy Policy:

https://insightglobal.com/workforce-privacy-policy/. Skills and Requirements Experience, Skills & Capabilities

• 1-3 years in software engineering, applied artificial intelligence (AI)/machine learning (ML), or clinical technology.
• Hands-on experience with large language model (LLM) orchestration or agentic AI platforms.
• Experience with AI-native engineering tools: Claude Code, Cursor, MCP integrations, or equivalent.
• Learns unfamiliar tools and systems quickly; demonstrates a track record of picking up new stacks or platforms without heavy ramp time.
• Experience producing tested outputs from formal specifications. Structured discovery experience is a plus.
• Strong prompt engineering skills: precise, auditable instructions.

Strong system integration skills:

API connections, connector configuration, and agent output flow into clinical systems.

• Ability to move quickly from a problem to a working build without dropping quality gates.
• Ability to produce structured documentation for build decisions and test results.
• Understanding of GxP regulatory requirements for audit trails, HITL gates, and confidence thresholds preferred.
• System-level thinking to identify reuse opportunities and drive consistency across builds.
• Comfortable navigating ambiguous inputs. Asks clarifying questions before building, not after.
• Effective collaborator in a distributed team environment.

MUST be able to work some PT hours, 6:00 am to 10:00 am PT Preference for Bangalore But open to Latam for hours!