דרושים Software Engineer with LLM Experience בתל אביב

Company Description

Sellence is an AI-powered, agentic B2C sales CRM that helps brands turn more leads into customers through automated, one-on-one sales experiences at scale.

We work with companies selling high-consideration products—insurance, wellness, healthcare, legal, real estate, home services, and more—where consumers demand personal, consultative sales conversations before they buy.

Historically, it wasn’t possible to deliver this kind of B2B-style sales experience to millions of B2C leads—but Sellence makes it not only possible, but automatic. Our platform enables brands to run personalized, human-like sales conversations 24/7, blending AI agents with live sales teams where needed. This hybrid approach drives more conversions, reduces CAC, and powers a faster, more intelligent revenue engine.

Over the past 4 months, we’ve doubled our client base and are on track to nearly double revenue. With tens of active clients and growing demand across industries, we're building the modern sales infrastructure for consumer businesses. Backed by top-tier investors, we’re entering our next stage of growth and are looking for exceptional engineers to build with us.

Role Description

We’re hiring a full-time Software Engineer with strong Python and LLM experience to join our Tel Aviv-based team (hybrid with remote flexibility). In this role, you will be a core architect of our product, responsible for designing, building, and scaling the AI engine that powers our agentic B2C sales CRM. You will create the robust, high-performance systems that enable our AI agents to conduct intelligent, human-like sales conversations, directly impacting our clients' success and our company's growth.

Responsibilities

• Develop, test, and deploy production-grade backend services and APIs that integrate with Large Language Models (LLMs).

• Engineer and refine complex prompt chains, agentic workflows, and function-calling logic within a scalable software architecture.

• Architect and implement robust Retrieval-Augmented Generation (RAG) systems using vector databases like Weaviate and PostgresML.

• Build and maintain data pipelines and evaluation frameworks to rigorously test and improve our AI models and prompt strategies.

• Design and optimize database schemas and write complex queries to support our AI systems and analytics needs.

• Collaborate closely with product and data science teams to translate business requirements into elegant technical solutions.

Qualifications

• 3+ years of professional software engineering experience with expert-level proficiency in Python.
• Proven experience building and deploying scalable, production-grade backend services (e.g., using FastAPI, and Asyncio).
• Strong proficiency in SQL is a must, with experience writing complex queries and working with relational databases.
• Deep hands-on experience with LLM APIs (e.g., OpenAI, Anthropic, Gemini) and a strong understanding of advanced prompt engineering principles.
• Practical experience designing and implementing solutions with vector databases such as Weaviate or PostgresML.
• Strong problem-solving, analytical, and system design skills.
• Bachelor’s degree in Computer Science, Engineering, or a related field.
• MSc in a relevant field is a strong plus.