Lead Engineer – Applied AI
Posted 17hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Lead/Staff Engineer building LLM agents and GenAI infrastructure for HighLevel’s AI-powered business operating system. Delivering scalable automation across communication, scheduling, sales, and operations.
Responsibilities:
- Architect and deploy autonomous AI agents for sales, messaging, scheduling, and operations workflows
- Build and fine-tune open-source and API-driven LLMs for HighLevel’s data and customer use cases
- Develop RAG systems and vector search infrastructure for context-rich, real-time generation
- Design and iterate on prompt engineering, context construction, and agent tool usage strategies using frameworks such as LangChain
- Apply modeling, A/B testing, scoring, clustering, and time-series forecasting to improve agent intelligence and product features
- Partner with backend, infrastructure, and product teams to build scalable GenAI infrastructure, including model serving, prompt versioning, logging, evaluations, and feedback loops
- Evaluate and monitor agent performance, hallucination rates, and real-world effectiveness through experimentation
- Influence HighLevel’s AI roadmap, mentor engineers, and contribute to technical standards and best practices
Requirements:
- 8+ years of experience in Data Science, Machine Learning, or Applied AI, with a track record of delivering production-grade models and systems
- Hands-on expertise with LLMs: fine-tuning, prompt engineering, function-calling agents, embeddings, and evaluation techniques
- Strong experience building retrieval-augmented generation (RAG) systems using vector databases such as FAISS, Pinecone, or Weaviate
- Experience in cloud-native environments including GCP and AWS
- Experience deploying models with PyTorch, Transformers (HF), and MLOps tools
- Experience with LangChain or similar agent orchestration frameworks
- Ability to design multi-step, tool-augmented agents
- Proficiency in Python and familiarity with TypeScript
- Strong engineering practices including CI/CD, testing, and versioning
- Knowledge of supervised and unsupervised learning, causal inference, statistical testing, segmentation, and time-series forecasting
- Experience taking ML/AI solutions from prototype to production, including monitoring, observability, and model iteration
- Ability to work independently and collaboratively, lead initiatives, and mentor peers
- Strong product sense and communication skills
- The role is categorized for India
Benefits:
- Remote-first organization
- Opportunity to work on high-impact, high-autonomy AI systems
- Mentoring and peer collaboration opportunities




















