AI & Automation Engineer

AI & Automation Engineer, Emergence | Remote (India) | Full-Time

Who We Are

Emergence is a PE holdco backed by the Pritzker Organization focused on acquiring and scaling B2B SaaS businesses. We combine operational rigor with a growth equity mindset to drive ARR growth and profitability across our portfolio.

The Mission

Build the intelligence layer that runs across Emergence's entire portfolio - agentic systems, LLM pipelines, and production integrations that become the operational backbone of multiple B2B SaaS businesses as we acquire and scale them. You're not building internal tooling. You're building infrastructure that compounds across companies.

What You'll Do

• Design and ship agentic systems and multi-step LLM workflows using Claude, OpenAI, or equivalent - including tool use, memory, structured output extraction, and failure handling

• Build and maintain MCP integrations connecting internal tools, portco systems, and external data sources into reliable, observable pipelines

• Own RAG pipeline architecture - chunking, embedding, retrieval evaluation, and continuous quality improvement against real usage data

• Write production-grade Python for data pipelines, integration scripts, and scheduled jobs running via BullMQ-backed queues on the Node/TypeScript stack

• Build and maintain REST API integrations across Salesforce, Ashby, SeekOut, Slack, and Google Workspace - owning reliability, retry logic, and failure alerting

• Own and evolve the browser automation layer, including Playwright-based scrapers with persistent session and anti-detection handling, while evaluating managed alternatives as the ecosystem matures

• Implement eval frameworks to test LLM outputs systematically and catch regressions before they reach production

• Track and optimize AI cost across models and workflows - model routing, prompt caching, token efficiency

What We're Looking For

Must-haves

• Agentic systems shipped in production - multi-step LLM workflows with tool use, not just single prompt calls

• RAG pipeline experience end to end - from chunking strategy through retrieval quality evaluation

• Strong Python - async patterns, modular code, structured logging, production-grade reliability

• Playwright or Selenium with real headless browser management in production

• REST API integration depth - rate limits, webhooks, retry logic, auth flows

• Experience integrating LLMs with live tools and data sources via APIs, function calling, or protocol layers (with MCP experience is strongly preferred)

• GitHub Actions - writing pipelines, not just using them

• Daily use of AI coding tools and a genuine understanding of where LLMs fail

Nice-to-haves

• LangGraph, CrewAI, or equivalent agentic framework experience

• N8N for workflow orchestration and automation

• A2A protocol experience for multi-agent systems

• Ashby, Salesforce, or SeekOut API experience

• Vector store experience - Pinecone, pgvector, Qdrant, or equivalent

• Grafana and Loki for observability

• Node.js and TypeScript familiarity enough to debug integration touchpoints

• AI eval framework experience - RAGAS, LangSmith, or custom evaluation pipelines

Who You Are

You build AI systems that work reliably in production, not just in demos. You reach for existing platforms and workflow tools before spinning up a custom service, and you can articulate clearly when building custom is the right call. You don't wait to be told the right approach, you form a view, pressure-test it, and advocate for it. You're as comfortable saying "we shouldn't build this" as you are building it.You treat LLM outputs as untrusted by default and build validation layers around them. You track cost and quality as first-class metrics. You've debugged a silent automation failure and you now instrument everything before shipping. You write Python the way a product engineer writes application code. You follow where the research is going and you've already used things that aren't widely adopted yet.

What We Offer

• Competitive compensation

• Direct ownership of AI and automation infrastructure

• Exposure to M&A and portfolio operations across multiple B2B SaaS companies

• Work that ships fast and shows up in real business outcomes, not internal backlogs

• A small team that hires slowly and expects a lot

• Remote-first, flexible hours, based in India