Role: Lead Developer – AI Velocity Engineering

Location: India (Remote / Hybrid)

Experience: 3-5 Years

Employment Type: Third-Party Payroll

About ZEISS VisioGen

ZEISS VisioGen is building the future of AI-powered healthcare by developing human-verified clinical communication solutions for ophthalmology practices. We combine cutting-edge Generative AI with clinical expertise to build scalable, production-ready applications that enhance patient engagement and improve healthcare delivery.

About the Role

We're looking for a hands-on developer to act as a force multiplier across our software development lifecycle - identifying friction in how we build and ship software, and using AI agents, automation, and process improvements to make engineering measurably faster and more productive. You look for problems instead of waiting for a ticket. You own, drive, and deliver outcomes end-to-end without handholding.

Exceptional ability to prioritize your own daily schedule, create your own backlog, and negotiate with functional engineering leads to ensure your tools get adopted.

What You'll Do

Hunt down and quantify SDLC friction : across requirements, coding, QA, regression, and documentation and eliminate it by building AI agents, skills, MCP, workflow automation, or simply optimized process fixes.

Build agentic solutions : prototype, design, develop and deploy AI agents and automations that remove bottlenecks, not just prototypes that sit on a shelf.

Automate Release Gates: Build and integrate custom agents directly into the Software Development Process (SWDP) to govern release control gates.

Deploy support and process agents :



including KB-driven RAG systems for internal teams and agents integrated into release control gates.

Own metrics and instrumentation : define and build product and engineering SLIs/SLOs, and get functional squads to adopt them.

Drive conversational and forensic analytics : ML/Agents to mine existing product’s conversation data to create unseen inferences, adoption friction, micro-personas correlations and produce insights, reports.

Be a technical force multiplier : evangelize and continuously optimize tooling and AI adoption across existing product squads.

Cost & Quality Conscious: Demonstrable ability to optimize LLM orchestration for accuracy and velocity while maintaining strict inference cost control.

Who You Are

3–5 years of hands-on development experience, Python-first (FastAPI, async, scripting, data parsing, pydantic,), with real production experience building AI/LLM-powered agents.

Skilled with GitHub Copilot and other AI-in-SDLC tooling as a core part of how you build production grade software.

Hands-on with LangChain/LangGraph or similar agentic frameworks.

Full-stack experience and comfortable in UI (React), backend services, custom API webhooks and integrations end-to-end.

Strong RAG pipelines and vector database experience; solid grounding in LLMs and the Azure AI ecosystem (Azure OpenAI, etc.), building Agentic workflows using Skills, MCPs, tool calls and evals.

Strong familiarity with continuous integration pipelines (Bitbucket, GitHub Actions, GitLab CI, Jenkins), automated quality gates, and containerization (Docker).

Comfortable with ambiguity, self-driven, bias to action.

Able to collaborate effectively with other engineering teams.

Able to operate within a regulated, enterprise (medtech) environment.

📌 Lead Developer - AI Velocity Engineering (India)
🏢 ZEISS VisioGen
📍 India