About the Role
We are looking for a Forward Deployed Engineer who thrives at the intersection of engineering, AI, and real-world business problems.
You will work directly with teams and functions to understand how they actually operate—not from behind a ticket queue, but by embedding yourself in their workflows, understanding their challenges, identifying opportunities, and building solutions that create measurable impact.
You will take ambiguous, complex problems and turn them into production-ready AI applications, agentic workflows, and automation solutions. This includes owning the solution end-to-end—from understanding the problem and working with users, to designing, building, deploying, and continuously improving the solution in production.
You are someone who is comfortable getting into the details: messy data, incomplete requirements, workflow exceptions, legacy integrations, changing priorities, and technical roadblocks. When a project is blocked because an integration is missing, data is inconsistent, or an engineering team is several sprints away from being available, you are the person who steps in and builds it.
This is a highly hands-on role. You will be measured by what you build, what reaches production, how effectively it solves the underlying problem, and the impact it creates—not by the number of tickets you close.
What You'll Do
- Embed with business, product, operations, or engineering teams to deeply understand their workflows, pain points, constraints, and edge cases.
- Identify the real problem behind the stated problem and translate ambiguous business challenges into practical technical solutions.
- Design and build AI-powered applications, intelligent automation, and agentic workflows that solve real business problems.
- Own solutions end-to-end, from discovery and architecture through development, deployment, monitoring, and continuous improvement.
- Build backend services primarily using Python, with Node.js where applicable.
- Design and implement LLM-powered applications, including prompt engineering, tool calling, structured outputs, model integration, and evaluation.
- Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, retrieval, reranking, and context management.
- Develop agentic systems capable of handling multi-step reasoning, tool use, workflow orchestration, state management, and exception handling.
- Implement memory and state-management capabilities for AI agents and applications.
- Integrate AI solutions with existing enterprise systems, APIs, databases, SaaS platforms, and internal tools.
- Build the cloud infrastructure and services required to run AI applications reliably in production.
- Troubleshoot issues across the stack—including application code, APIs, data pipelines, AI/LLM behavior, integrations, and infrastructure.
- Handle the challenges that typically derail delivery: incomplete or inconsistent data, undocumented processes, workflow exceptions, missing integrations, and evolving requirements.
- Work closely with users and stakeholders to test solutions in real-world environments, gather feedback, and iterate rapidly.
- Monitor production solutions and continuously improve accuracy, reliability, latency, scalability, cost, and user experience.
- Establish appropriate guardrails, observability, security, and evaluation mechanisms for production AI systems.
- Partner with engineering, product, data, and business teams to ensure solutions are scalable and maintainable.
- Act as a technical problem solver who can move quickly from this is a problem to this is working in production.
- Share learnings, reusable patterns, and best practices to accelerate the adoption of AI across teams and functions.
Required Qualifications
- 6+ years of overall software engineering experience, with at least 2+ years of hands-on experience building AI/GenAI solutions.
- Strong software engineering fundamentals with experience building and deploying production-grade applications.
- Strong proficiency in Python; experience with Node.js/TypeScript is a plus.
- Hands-on experience building applications using LLMs and Generative AI.
- Strong understanding of agentic AI architectures and AI workflow orchestration.
- Experience with RAG architectures, embeddings, vector databases, retrieval strategies, and context optimization.
- Experience working with LLM APIs and frameworks such as OpenAI, Anthropic, Gemini, LangChain, LangGraph, LlamaIndex, or equivalent technologies.
- Strong experience working with REST APIs, microservices, databases, authentication, and third-party integrations.
- Experience deploying applications on at least one major cloud platform such as AWS, Azure, or GCP.
- Strong understanding of containers, CI/CD, cloud services, logging, monitoring, and production operations.
- Experience working with unstructured and/or messy enterprise data.
- Strong debugging and problem-solving skills across application, data, AI, and infrastructure layers.
- Ability to work independently in ambiguous environments and make sound technical decisions with limited direction.
- Strong communication skills with the ability to work directly with business users, product managers, engineering teams, and senior stakeholders.
Preferred Qualifications
- Experience building AI agents that use tools, APIs, databases, or enterprise applications to complete multi-step workflows.
- Experience with MCP (Model Context Protocol) or similar approaches to connecting AI agents with enterprise tools and systems.
- Experience with AI evaluation frameworks, observability, guardrails, and LLM performance monitoring.
- Experience with PostgreSQL, Redis, vector databases, or similar data technologies.
- Experience with Docker, Kubernetes, Terraform, or other modern infrastructure technologies.
- Experience building event-driven or asynchronous systems.
- Understanding of AI security, data privacy, access controls, and responsible AI practices.
- Experience taking AI/GenAI prototypes from POC to production at scale.
- Experience working in a consulting, startup, product engineering, or highly customer-facing environment.