Role Overview
As a Context Engineer, you will play a central role in developing AI infrastructure that powers intelligent interactions within a financial technology platform. Your work will bridge advanced language models and real-world financial applications, focusing on building systems that are not only technically sound but also operationally resilient and aligned with regulated environments.
Key Responsibilities
- Integrate large language models into core platform functionality using model APIs from providers like Anthropic, OpenAI, and Cohere, prioritizing system stability and long-term maintainability
- Design and manage retrieval-augmented generation pipelines that connect models to internal data sources, databases, and live feeds using vector storage and semantic search
- Develop strategies for context handling—determining what data is passed to models, how it’s structured, and when it’s updated—to balance performance, cost, and response quality
- Build autonomous, multi-step workflows that allow the platform to execute complex tasks with minimal human intervention
- Implement safeguards and validation logic to ensure AI outputs remain within defined operational and compliance boundaries
- Create reusable components, prompt patterns, and agent building blocks to accelerate development across engineering teams
- Construct evaluation systems to track the effectiveness of context usage, output accuracy, and agent behavior in live environments
- Monitor deployed AI features for anomalies, identify root causes, and apply fixes that improve system resilience over time
- Partner with Product, Engineering, Implementation, and Data teams to turn business needs and prototypes into scalable, production-ready AI solutions
- Support internal knowledge growth by mentoring engineers and sharing best practices in context design and agent-based systems
Qualifications
You bring a solid foundation in software engineering with a focus on real-world AI integration. You understand the challenges of deploying models beyond prototypes and are committed to building systems that last.
- 5+ years of professional software development experience, including 1–2 years working with LLMs in production environments
- Proficiency in Python or Node for backend services and API integrations
- Hands-on experience with orchestration frameworks and execution pipelines
- Proven work with RAG systems, vector databases (e.g., Pinecone, pgVector, AWS OpenSearch), and semantic search techniques
- Understanding of context optimization methods such as summarization, chunking, session management, and memory patterns
- Experience integrating third-party APIs and external services into backend systems
- Ability to work effectively in cross-functional, fast-moving teams within high-growth settings
- Strong analytical mindset and adaptability in a rapidly evolving technical domain
Preferred Experience
- Knowledge of Model Context Protocol (MCP) or similar tool-interfacing standards
- Experience with LLMOps: tracing, observability platforms (e.g., LangSmith, Datadog), and model lifecycle management
- Exposure to multi-agent architectures and workflow orchestration patterns
- Understanding of AI governance, output validation, and context safety—especially in regulated domains like financial services
- Familiarity with AWS cloud infrastructure and containerized deployments using Docker and Kubernetes
- Ability to explain complex technical concepts clearly to both engineers and non-technical stakeholders
Technology Environment
Our stack includes Python, Node, REST APIs, and integrations with leading LLM providers including Anthropic, OpenAI, and Cohere. We use Pinecone, pgVector, and AWS OpenSearch for vector storage, with Docker and Kubernetes for deployment. Observability is supported through LangSmith and Datadog.
Culture & Values
We prioritize scalable innovation and real-world impact over flashy demos. Our culture emphasizes collaboration between engineering, product, and domain specialists, with a strong commitment to learning, reliability, and shared knowledge. We support internal upskilling and value engineers who are curious, pragmatic, and focused on long-term system health.
