• Design, build, and deploy advanced AI solutions using LLMs, RAG, embeddings, vector databases, semantic search, and agentic architectures. • Develop intelligent systems that can process documents, retrieve knowledge, generate content, automate workflows, and transform unstructured data into actionable insights. • Work with modern GenAI and AI engineering tools such as LangChain, LangGraph, Hugging Face, PyTorch, MCP, multi-agent frameworks, and cloud-native AI services. • Build scalable, reliable AI applications across Azure, AWS, Databricks, or similar cloud/data platforms. • Experiment with and evaluate foundation models, prompts, retrieval strategies, orchestration patterns, and performance optimization techniques. • Collaborate closely with engineering, product, data, and business teams to define the right technical approach and deliver high-impact AI solutions. • Stay plugged into the fast-moving GenAI ecosystem and bring new ideas, tools, and prototypes into real-world applications.

Role Description We are seeking a Staff Software Engineer - AI to join our Engineering team. In this role, you will build the mission-critical AI infrastructure and cohesive data layer that powers intelligent agents and applications serving health insurance plans covering over 15 million people. You'll partner closely with product, data science, and clinical teams to build the foundation that transforms how clinical intelligence is delivered at scale. This is an opportunity to make a direct impact on healthcare outcomes while working with modern technologies in a fast-paced, collaborative environment. What you’ll do: - Strategic Contribution: - Drive the technical vision and roadmap for Cohere’s AI-powered agents, applications, and platforms, ensuring scalable, reusable, and high-performance solutions. - Partner with enterprise architecture to define standards and ensure designs meet key non-functional requirements (observability, performance, operational readiness). - Technical Execution & Code Quality: - Lead the design and delivery of production-ready systems, including data and retrieval architectures that provide AI agents with the right context across healthcare data sources. - Own code quality through active code reviews, release leadership, deployments, and on-call support, ensuring systems are reliable, scalable, and compliant with healthcare standards (e.g., HIPAA). - Cross-Functional Collaboration: - Partner with product, ML/DS, clinical, and architecture teams to translate requirements into effective, end-to-end technical solutions, contributing to planning, design, and delivery. - Team Enablement & Mentorship: - Mentor and support engineers across levels, unblocking work, elevating technical quality, and improving team effectiveness through best practices and continuous improvement. Qualifications - 10+ years of experience building and delivering complex, production-grade software systems, with deep expertise in modern development practices, cloud environments, and scalable architecture. - Strong background designing data systems and pipelines that support AI-driven applications, with solid fundamentals in data modeling, data quality, and working across diverse data sources. - Experience working with modern AI systems and applying them in real-world, production environments. - Proven ability to define technical direction, influence system design across teams, and communicate complex concepts to both technical and non-technical stakeholders. - Track record of mentoring engineers and contributing to engineering standards, frameworks, or best practices that improve team-wide effectiveness. - Bachelor’s degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience. Benefits - 💻 Fully remote opportunity with about 5% travel. - 🩺 Medical, dental, vision, life, disability insurance, and Employee Assistance Program. - 📈 401K retirement plan with company match; flexible spending and health savings account. - 🏝️ Flex Time Off + company holidays. - 👶 Up to 14 weeks of paid parental leave. - 🐶 Pet insurance. Company Description Cohere Health’s clinical intelligence platform delivers AI-powered solutions that streamline access to quality care by improving payer-provider collaboration, cost containment, and healthcare economics. Cohere Health works with over 660,000 providers and handles over 12 million prior authorization requests annually. Its responsible AI auto-approves up to 90% of requests for millions of health plan members. With the acquisition of ZignaAI, we’ve further enhanced our platform by launching our Payment Integrity Suite, anchored by Cohere Validate™, an AI-driven clinical and coding validation solution that operates in near real-time. By unifying pre-service authorization data with post-service claims validation, we’re creating a transparent healthcare ecosystem that reduces waste, improves payer-provider collaboration and patient outcomes, and ensures providers are paid promptly and accurately. Cohere Health’s innovations continue to receive industry-wide recognition. We’ve been named to the 2025 Inc. 5000 list and in the Gartner® Hype Cycle™ for U.S. Healthcare Payers (2022-2025), and ranked as a Top 5 LinkedIn™ Startup for 2023 & 2024. Backed by leading investors such as Deerfield Management, Define Ventures, Flare Capital Partners, Longitude Capital, and Polaris Partners, Cohere Health drives more transparent, streamlined healthcare processes, helping patients receive faster, more appropriate care and higher-quality outcomes. The Coherenauts, as we call ourselves, who succeed here are empathetic teammates who are candid, kind, caring, and embody our core values and principles. We believe that diverse, inclusive teams make the most impactful work. Cohere is deeply invested in ensuring that we have a supportive, growth-oriented environment that works for everyone. We can’t wait to learn more about you and meet you at Cohere Health! Equal Opportunity Statement Cohere Health is an Equal Opportunity Employer. We are committed to fostering an environment of mutual respect where equal employment opportunities are available to all. To us, it’s personal.

• Conversational Agent Development: Build and evolve AI agents for customer service, negotiation, and conversion across channels such as WhatsApp, voice, and webchat. • LLM Orchestration: Implement flows using frameworks like LangGraph (or similar), managing context, memory, tools (tool calling), and conversation states. • Prompt Engineering: Create, test, and optimize prompts for different scenarios (collections, sales, support), ensuring consistency and performance. • Tool Integration: Connect agents to APIs and external systems (e.g., Pix payment generation, data lookup, CRM), enabling in-conversation actions. • AI Quality Control: Monitor responses, prevent hallucinations, and ensure adherence to business rules. • Personalization: Work with contextual data (customer profile, history, segmentation) to make interactions smarter and more effective. • Experimentation: Run A/B tests on approaches, flows, and prompts, continuously improving agent performance. • AI Observability: Track usage, cost, latency, and response quality metrics (LLM monitoring). • Cost Optimization: Implement strategies to reduce cost per interaction (model selection, caching, fallbacks, etc.). • Collaboration: Work closely with backend, product, and operations teams to ensure AI delivers real business impact.

• Build and maintain APIs that integrate generative AI models into production systems, with a focus on scalability and low latency. • Collaborate with cross-functional teams to identify use cases for generative AI, define requirements, and contribute to impactful solutions. • Implement and optimize workflows for model inference using large-scale pre-trained models. • Contribute to generative AI model pipelines, supporting monitoring and ongoing performance. • Conduct experiments to evaluate generative AI models against real-world performance metrics such as fluency, coherence, and factual accuracy. • Stay current with advancements in generative AI research and help integrate new techniques into the organization’s capabilities. • Support the reliability, scalability, and security of generative AI systems in deployment. • Document processes, architectures, and technical decisions to facilitate collaboration and future improvements.