What You'll Do

• Design, build, test, and operate production-grade agentic AI applications and services.

• Contribute to the design and implementation of shared agentic AI capabilities, including:

• Agent frameworks and orchestration

• Planning, tool use, and memory strategies

• Retrieval-Augmented Generation (RAG) pipelines

• LLM integration and inference services

• Evaluation, observability, and safety tooling

• Partner with senior engineers to design scalable, reliable, and maintainable distributed systems.

• Participate in technical design discussions and code reviews, helping improve engineering quality across the team.

• Collaborate with Product, UX, and cross-functional partners to deliver AI-powered capabilities from concept through production.

• Evaluate emerging AI technologies and help incorporate practical improvements into our platform.

• Mentor junior engineers and contribute to a collaborative engineering culture.

Technical Environment

We don't hire to a narrow checklist, but successful candidates should be comfortable working in a modern, cloud-native engineering environment with an emphasis on agentic AI.

Core Engineering Stack

• Languages: Go, TypeScript, Python

• APIs: REST, gRPC, and tRPC

• Cloud: AWS and/or GCP

• SNS, SQS, Lambda, EKS, API Gateway

• Kubernetes

• Distributed systems and event-driven architectures (Kafka)

• Durable Execution frameworks, like Temporal or DBOS

• Orchestration frameworks such as LangGraph, LangChain, Airflow, or similar

Agentic AI and ML

• Integrating commercial and open-source LLMs into production applications

• Agent and orchestration frameworks such as VercelAI SDK, LangChain, LangGraph, LlamaIndex, etc.

• Retrieval-Augmented Generation (RAG) architectures

• Embedding Models and Vector Databases

• Multi-agent orchestration and agent harness development

• Prompt engineering and structured output generation

• Model serving, embeddings, and inference tooling

• Familiarity with Effect TS library

• Schema validation and state management using tools such as Zod (TypeScript)

• Emphasize evaluation, observability, safety, and reliability to support AI solutions deployed in a regulated, customer-facing environment.

What We're Looking For

• 6+ years of experience building large-scale backend or distributed software systems.

• Experience developing AI-powered applications using LLMs, agentic workflows, RAG, or modern ML platforms.

• Experience building production services using TypeScript, Go, Python or similar languages.

• Strong software engineering fundamentals across backend development, APIs, cloud infrastructure, and distributed systems.

• Familiarity with cloud platforms, containers, and Kubernetes.

• Experience with asynchronous processing, workflow engines, queues, or streaming systems.

• Strong problem-solving skills and the ability to work through ambiguous technical challenges.

• Excellent collaboration and communication skills, with the ability to work effectively across engineering and product teams.

• Passion for learning new technologies and contributing to engineering best practices.

Preferred Qualifications

• Experience building AI applications in financial services or other regulated industries.

• Experience deploying production LLM or RAG-based systems.

• Familiarity with evaluation frameworks, observability, and AI safety practices.

• Contributions to open-source software or AI-related projects.

• Experience with fine-tuning, model optimization, or inference pipelines is a plus.