Senior AI Engineer

Apollo.io

7d•Remote

About The Position

Apollo.io is the leading go-to-market solution for revenue teams, trusted by over 500,000 companies and millions of users globally, from rapidly growing startups to some of the world's largest enterprises. Founded in 2015, the company is one of the fastest growing companies in SaaS, raising approximately $250 million to date and valued at $1.6 billion. Apollo.io provides an end-to-end go-to-market platform that enables sales and marketing teams to source prospects from our database of 210 million B2B contacts and 35 million companies, execute personalized email outreach campaigns, automate booking flows, and manage deals—all within one unified platform. Apollo raised a Series D in 2023 and is backed by top-tier investors, including Sequoia Capital, Bain Capital Ventures, and more, and counts the former President and COO of Hubspot, JD Sherman, among its board members. We are AI Native Apollo.io is an AI-native company built on a culture of continuous improvement. We're on the front lines of driving productivity for our customers—and we expect the same mindset from our team. If you're energized by finding smarter, faster ways to get things done using AI and automation, you'll thrive here. Your Role & Mission As a Senior AI Engineer on our AI Engineering team, you will be responsible for building and productionizing advanced AI systems powered by Large Language Models (LLMs) and intelligent agents. You'll work on critical Apollo capabilities including our AI Assistant, Autonomous AI Agents, Deep Research Agents, Conversational Assistant, Semantic Search, Search Personalization, and AI Power Automation features that directly impact millions of users' productivity. The mission of our AI teams is to leverage Apollo's massive scale data and cutting-edge AI to understand and predict user behaviors, personalize experiences, and optimize every stage of the customer journey through intelligent automation. What You'll Be Working On AI Assistant & Agent Systems Agent Architecture & Implementation: Build sophisticated multi-agent systems that can reason, plan, and execute complex sales workflows Context Management: Develop systems that maintain conversational context across complex multi-turn interactions LLM and Agentic Platforms: Build scalable large language model and agentic platforms that enable widespread adoption and viability of agent development within the Apollo ecosystem Backend Systems: Build back-end systems necessary to support the agents. AI features: Conversational AI, Natural Language Search, Personalized Email Generation and similar AI features Classical AI/ML (Optional Focus) Search Scoring & Ranking: Develop and improve recommendation systems and search relevance algorithms Entity Extraction: Build models for automatic company keywords, people keywords, and industry classification Lookalike & Recommendation Systems: Create intelligent matching and suggestion engines

Requirements

8+ years of software engineering experience with a focus on production systems
1.5+ years of hands-on LLM experience (2023-present) building real applications with GPT, Claude, Llama, or other modern LLMs
Production LLM Applications: Demonstrated experience building customer-facing, scalable LLM-powered products with real user usage (not just POCs or internal tools)
Agent Development: Experience building multi-step AI agents, LLM chaining, and complex workflow automation
Prompt Engineering Expertise: Deep understanding of prompting strategies, few-shot learning, chain-of-thought reasoning, and prompt optimization techniques
Python Proficiency: Expert-level Python skills for production AI systems
Backend Engineering: Strong experience building scalable backend systems, APIs, and distributed architectures
LangChain or Similar Frameworks: Experience with LangChain, LlamaIndex, or other LLM application frameworks
API Integration: Proven ability to integrate multiple APIs and services to create advanced AI capabilities
Production Deployment: Experience deploying and managing AI models in cloud environments (AWS, GCP, Azure)
Testing & Evaluation: Experience implementing rigorous evaluation frameworks for LLM systems including accuracy, safety, and performance metrics
A/B Testing: Understanding of experimental design for AI system optimization
Monitoring & Reliability: Experience with production monitoring, alerting, and debugging complex AI systems
Data Pipeline Management: Experience building and maintaining scalable data pipelines that power AI systems

Nice To Haves

You've built AI systems that real users depend on, not just demos or research projects
You understand the difference between a working prototype and a production-ready system
You have experience with user feedback, iterative improvements, and feedback systems
You can design end-to-end systems, including back-end systems, asynchronous workflows, LLMs, and agentic systems
You understand the cost-benefit trade-offs of different AI approaches
You've made decisions about when to use different LLM providers, fine-tuning vs prompting, and architecture choices
You implement repeatable, quantifiable evaluation methodologies
You track performance across iterations and can explain what makes systems successful
You prioritize safety, reliability, and user experience alongside capability
You stay current with the rapidly evolving LLM landscape
You can quickly adapt to new models, frameworks, and techniques
You're comfortable working in ambiguous problem spaces and breaking down complex challenges

Responsibilities

Design and Deploy Production LLM Systems: Build scalable, reliable AI systems that serve millions of users with high availability and performance requirements
Agent Development: Create sophisticated AI agents that can chain multiple LLM calls, integrate with external APIs, and maintain state across complex workflows
Prompt Engineering Excellence: Develop and optimize prompting strategies, understand trade-offs between prompt engineering vs fine-tuning, and implement advanced prompting techniques
System Integration: Build robust APIs and integrate AI capabilities with existing Apollo infrastructure and external services
Evaluation & Quality Assurance: Implement comprehensive evaluation frameworks, A/B testing, and monitoring systems to ensure AI systems meet accuracy, safety, and reliability standards
Performance Optimization: Optimize for cost, latency, and scalability across different LLM providers and deployment scenarios
Cross-functional Collaboration: Work closely with product teams, backend engineers, and stakeholders to translate business requirements into technical AI solutions