Staff Applied AI Engineer

Invoca

4h•Remote

About The Position

Are you passionate about harnessing the power of generative AI and foundation models to build truly intelligent products? At Invoca, we're a team of innovators committed to building exceptional teams and groundbreaking AI solutions. This is a unique opportunity to architect the next generation of AI-powered customer experiences, making a direct and measurable impact on our products and the success of our clients. Why You'll Thrive Here As a key member of our Data Platform team, you won't just build models; you'll architect the future of how businesses understand and interact with their customers. You will: Architect and Deploy Applied AI Systems: Design, build, and deploy scalable, production-grade applications using foundation models and other advanced AI techniques to directly influence product performance and efficiency. Engineer Advanced RAG and Agentic Systems: Go beyond basic implementation. Engineer robust Retrieval-Augmented Generation (RAG) pipelines and multi-step agentic workflows that can reason, use tools, and solve complex problems. Contribute to Agentic AI System Evaluation: Establish and manage rigorous evaluation frameworks for complex AI agents. You will go beyond simple response quality to assess the entire agentic process, including the validity of reasoning steps, correctness of tool use, task completion rates, and overall robustness. Excel in Prompt Engineering and Optimization: Craft, test, and manage sophisticated prompt chains and templates to ensure optimal performance, reliability, and cost-effectiveness from our AI models. Build for Scale and Reliability: Develop resilient serving architectures that seamlessly integrate Large Language Models (LLMs) with enterprise systems, ensuring high availability and performance. Champion MLOps for Applied AI: Develop and maintain sophisticated MLOps and CI/CD pipelines tailored for the unique challenges of generative AI, including prompt versioning, RAG pipeline management, and continuous evaluation of agent behavior. Translate Business Needs into AI-Powered Solutions: Work as a strategic partner to product and engineering teams, deeply understanding customer challenges and translating them into innovative, viable, and impactful AI features. At Invoca, Applied AI Engineers are empowered by mentorship from leading experts across our data science, engineering, and architecture teams. Our dedicated data platform team leverages a powerful combination of proprietary, patented technologies and best-in-class vendor tools to create an exceptionally scalable AI application platform. Our goal is to seamlessly deliver transformative AI-powered experiences through our robust API platform, and your expertise will contribute significantly in accelerating this mission.

Requirements

5+ years of professional experience in Applied AI Engineering, ML Engineering, or a closely related role with a strong focus on building and deploying AI-powered products and applications.
Advanced proficiency in Python and hands-on experience building applications with leading AI/ML frameworks (e.g., LangChain, LlamaIndex, CrewAI, PyTorch). You are an expert with data and ML libraries (e.g., Pandas, spaCy).
Demonstrated success deploying and maintaining applications powered by LLMs and other generative models in a production environment.
Deep, hands-on experience designing, building, and optimizing RAG pipelines. This includes expertise in vector databases (e.g., Qdrant, Pinecone, Weaviate), embedding strategies, and chunking techniques.
Demonstrable experience with modern evaluation techniques for multi-step AI agents. You should be able to speak to the trade-offs of evaluating reasoning traces, tool usage, and final outcomes using frameworks like LangSmith, DeepEval, Ragas, TruLens, or custom-built solutions.
Demonstrable skill in designing, testing, and optimizing complex prompts and few-shot examples to maximize model performance for specific tasks.
Experience in fine-tuning foundation models for specific downstream tasks, with a clear understanding of when to fine-tune versus when to use in-context learning or agentic approaches.
Advanced proficiency with API-driven frameworks for accessing and serving self-hosted foundation models (e.g., AWS SageMaker/Bedrock, Databricks Model Serving, TGI, vLLM), focusing on building resilient, scalable, and optimized integrations.
A proven ability to optimize AI systems for low latency and high throughput. You have experience with techniques like model quantization, caching strategies, and infrastructure choices to manage and reduce operational costs.
Intermediate proficiency with MLOps tooling (e.g., MLFlow, Arize), and best practices for CI/CD, monitoring, and maintenance of complex AI systems.
Bachelor's Degree in Computer Science, Engineering, Statistics, or a related field (or equivalent practical experience).

Nice To Haves

An advanced degree (Master's or Ph.D.) is a strong plus.

Responsibilities

Design, build, and deploy scalable, production-grade applications using foundation models and other advanced AI techniques to directly influence product performance and efficiency.
Engineer robust Retrieval-Augmented Generation (RAG) pipelines and multi-step agentic workflows that can reason, use tools, and solve complex problems.
Establish and manage rigorous evaluation frameworks for complex AI agents. You will go beyond simple response quality to assess the entire agentic process, including the validity of reasoning steps, correctness of tool use, task completion rates, and overall robustness.
Craft, test, and manage sophisticated prompt chains and templates to ensure optimal performance, reliability, and cost-effectiveness from our AI models.
Develop resilient serving architectures that seamlessly integrate Large Language Models (LLMs) with enterprise systems, ensuring high availability and performance.
Develop and maintain sophisticated MLOps and CI/CD pipelines tailored for the unique challenges of generative AI, including prompt versioning, RAG pipeline management, and continuous evaluation of agent behavior.
Work as a strategic partner to product and engineering teams, deeply understanding customer challenges and translating them into innovative, viable, and impactful AI features.

Benefits

Flexible Time Off – We encourage a healthy work-life balance. Our flexible paid time off policy allows you to recharge and take time away as needed.
Paid Holidays – Invoca provides 16 U.S. paid holidays, including a winter break, giving you ample opportunity to refresh and spend time with friends and family.
Health Benefits – Our healthcare program includes medical, dental, and vision coverage, with multiple plan options so you can choose what works best for you and your family. Fertility assistance is also included.
Retirement – Invoca offers a 401(k) plan through Fidelity with a company match of up to 4%.
Stock Options – All employees are invited to share in Invoca’s success through stock options.
Mental Health Program– Well-being support on a broad range of issues is available through our SpringHealth program.
Paid Family Leave – Up to 6 weeks of 100% paid leave is provided for baby bonding, adoption, and caring for family members.
Paid Medical Leave – Up to 12 weeks of 100% paid leave is provided for childbirth and medical needs.
InVacation – As a thank-you to our long-term team members, we offer a bonus after 7 years of service.
Wellness Subsidy – We provide a subsidy that can be applied toward gym memberships, fitness classes, and more.