You will play a critical role in building agents, automating internal tools to improve efficiency, developing AI-powered applications to meet the needs of internal stakeholders and customers, and prototyping/experimentation. You’ll have a unique opportunity to work closely with leadership, help develop our AI strategy, and tackle innovative projects.
Build sophisticated agents from scratch using whatever technology gets the job done, designing multi-agent systems that communicate, collaborate, and execute complex operations with minimal human intervention, developing and integrating Model Context Protocols (MCP) that elevate the agents' capabilities beyond current limitations, and identifying and obliterating inefficiencies in workflows through intelligent automation that actually works.
Shape the future of AI within Apptegy's product suite by embedding cutting-edge LLM capabilities directly into user experiences. Solve complex problems at the intersection of product, engineering, and artificial intelligence. Mentor an engineering organization, establish AI best practices, and see your strategic vision come to life, growing your leadership and technical expertise.
Build agentic AI systems that solve real-world connectivity and support problems through planning, tool use, and multi-step reasoning. Lead the effort in evaluating LLM usage for safety, correctness, hallucination, contextual relevance, and performance—ensuring the right model is used for the job. Design robust prompts and workflows to support voice and text-based interactions across a wide variety of customer environments.
As the first dedicated AI Engineer, you’ll research, prototype, and productionize machine-learning and generative-AI models that power new features and sharpen existing ones. You’ll be the bridge between cutting-edge research and real-world impact, contributing to the seamless integration of AI components into the backend.
Play a key role in designing, building, and maintaining AI-powered enterprise applications. Work closely with product managers, designers, and engineers to deliver innovative software solutions that solve high-stakes problems for our customers. The primary focus will be on Screens, an AI-powered contract review application, where cutting-edge techniques using LLMs, RAG, and AI agent frameworks are applied.
Build a real-time Voice & Video AI Agent that can talk to candidates over audio/video (WebRTC). Integrate LLMs (OpenAI, Claude, Mistral, etc.) and RAG pipelines to drive contextual conversations. Develop interview scoring, persona emulation, and agent memory. Work on agentic orchestration for seamless dialog management and multi-agent collaboration. Optimize for low-latency, high-fidelity conversations.
At the forefront of developing intelligent, user-centric solutions that assist scientists and internal teams throughout their research journey—from experimental design and data processing to troubleshooting and advanced analysis. Design, build, test, and deploy scalable and efficient backend systems that power AI- and LLM-driven customer experiences and internal tools.
Investigation of custom parsing methods for technical documents as a preparation step for vector database embedding; Fine-tuning and extension of LLMs for domain-specific use in industrial hydraulics; Evaluation of prompt-tuning methods for tailored results from LLMs.
Build and ship features for North, Cohere's AI workspace platform. Develop autonomous agents that talk to sensitive enterprise data. Write and ship minimal code that runs in low-resource environments, and has highly stringent deployment mechanisms. Security and privacy are paramount, so you will sometimes need to re-invent the wheel, and won’t be able to use the most popular libraries or tooling. Collaborate with researchers to productionize state-of-the-art models and techniques.