Forward Deployed Engineer

• 6+ Years of Experience: Proven background in full-stack or AI/ML software engineering with a strong track record of shipping production software.
• Hands-on GenAI Expertise: Deep familiarity with modern Generative AI patterns, including agents, multi-agent frameworks, RAG, prompt engineering, and LLM evaluation strategies.
• Agentic Ecosystem Knowledge: Direct experience with MCP (Model Context Protocol) servers, headless/background agents, and harness engineering patterns.
• Core Tech Stack: Strong proficiency in Python and solid capability in TypeScript/JavaScript, Go, or equivalent.
• Startup / Innovation Mindset: Prior experience in a startup, R&D lab, or fast-paced innovation team where speed to market is critical.
• AI-Native Engineer: Daily mastery of modern AI coding assistants (e.g., Claude Code, GitHub Copilot, Databricks AI Assistant, Cursor) as your primary development workflow.

Nice to Have

• Experience operating in regulated industries (e.g., Pharmaceuticals, Healthcare, Financial Services).
• Familiarity with compliance standards and governance frameworks such as GxP, GDPR, or SOX.

,[Agentic Systems & GenAI Development: Architect, build, and deploy sophisticated GenAI solutions, including multi-agent orchestration systems, autonomous headless agents, harness engineering, and advanced RAG architectures., Full-Stack AI Engineering: Write clean, production-grade code across the stack using Python alongside TypeScript/JavaScript, Go, or similar modern languages., Model Context Protocol (MCP) Integration: Build, extend, and maintain MCP servers and agent toolings to seamlessly connect AI agents with external systems, APIs, and data stores., Rapid Prototyping to Production: Turn rough sketches and concepts into robust, working software at high speed, maintaining quality while moving fast., AI-First Workflow: Leverage AI coding assistants as your primary development interface to accelerate solution delivery and maintain high velocity., Production Evaluation & Reliability: Implement evaluation frameworks to benchmark agent performance, accuracy, hallucination rates, and latency in production environments.] Requirements: AI, ML, RAG, LLM, Python, TypeScript, JavaScript, Go, R, Claude, GitHub, Databricks, GXP, GDPR