LLM jobs

Launched in 2018, Forethought is the first AI-native platform for enterprise customer support, built on a multi-agent architecture for omnichannel resolution. Trusted by leading companies like Upwork, Grammarly, Airtable, and Datadog, Forethought’s AI agents resolve billions of monthly support issues. The company has raised $115M+ in venture funding from top investors, including Blue Cloud Ventures, NEA, Village Global, and Sound Ventures, G2 has recognized Forethought as a High Performer in 2024 and Mid-Market Leader, Best Est. ROI, and Easiest to Do Business With in Customer Support for 2025.

We’re looking for talented Backend Engineers with a growth mindset—engineers who thrive on solving complex challenges and want to help shape the future of AI-driven customer support.

As an engineer on the team, you’ll play a critical role in designing, building, and deploying AI-powered features that directly impact how users experience and interact with our platform. You’ll work across systems leveraging state-of-the-art tools and infrastructure to deliver intelligent, scalable customer support solutions. Our tech stack leverages modern technologies, including Docker, Kubernetes, Redis, MongoDB, and ElasticSearch.

What You'll Be Doing (Responsibilities):

• Design and build backend services that power Forethought’s core AI features, directly impacting the customer experience across our platform.
• Collaborate with product and design teams to translate user needs into scalable backend solutions that enhance customer support automation.
• Scale and optimize our product to handle over 1 billion monthly interactions, ensuring high performance, reliability, and efficiency across all customer touchpoints.
• Partner with AI/ML engineers to integrate LLM-based capabilities into production workflows, with a focus on reliability, observability, and speed.
• Drive technical excellence by owning projects end-to-end—from architecture and implementation to deployment and monitoring.

Who You Are (Requirements): 

• A Bachelor’s or Master’s degree in Computer Science, Statistics, Informatics, Information Systems, or a related field is preferred.
• Demonstrated 3+ years of experience in a software engineering role is required.
• Expertise in Python is essential with proficiency in one of the mainstream Python frameworks (FastAPI/Django/Flask)
• Proven experience in constructing large-scale distributed systems is necessary.
• Ability to craft high quality, well-tested code to address customer requirements.
• Experience with MongoDB, Redis, and Elasticsearch is preferred.
• Experience working with generative AI frameworks (e.g., LangChain, RAG pipelines, multi-agent systems) is a plus.
• Familiarity with integrating and building applications on top of large language models (e.g., OpenAI, Anthropic, open-source LLMs) is highly valued.

**The anticipated salary range for this role based on location, and experience will be approximately $130,000 - $210,000 (base). This amount does not include bonuses or equity that will also be included in the offer.