Forward Deployed Engineer

• Work embedded with client and Sia teams, taking part in planning, stand-ups, and delivery activities.
• Run technical discovery with client stakeholders and turn business needs into scoped, buildable deliverables with clear acceptance criteria.
• Build production-grade Python services and APIs (FastAPI and REST) that power Generative AI applications, including RAG pipelines over enterprise knowledge sources.
• Integrate LLM APIs and SDKs into client environments, handling authentication, rate limits, fallbacks, latency, and cost.
• Connect solutions to enterprise systems such as databases, internal APIs, document stores, and business applications.
• Deploy and release services on AWS, Azure, or GCP using Docker and CI/CD, working within the client's codebase and engineering standards.
• Apply testing, observability and monitoring; lead production troubleshooting and root-cause analysis.
• Apply security, reliability and performance practices from the start, including secrets handling, access control and data protection.
• Estimate effort, flag risks and dependencies early, and communicate trade-offs and progress openly to technical and non-technical stakeholders.
• Document decisions, hand over knowledge, and train client teams so the solution can be operated and adopted.
• Capture reusable components and lessons from each engagement and contribute them back to the AI Factory.

Education and experience:

• Bachelor's or Master's degree in Computer Science, Engineering or a related field, or equivalent practical experience.
• 3 to 6 years of professional software engineering experience, with a focus on Python backend development.
• At least one Generative AI or LLM-based solution delivered to production, with clear personal ownership.
• Experience in governed enterprise environments, including security reviews and change processes.
• Fluent professional English, written and spoken.

Technical skills (required):

• Strong Python with production experience, including FastAPI or an equivalent web framework and REST API design.
• Backend and microservices design: service boundaries, asynchronous processing, error handling, and automated testing.
• Ability to work productively in unfamiliar codebases and follow existing engineering standards.
• SQL and relational data modeling, and working experience with at least one vector database or vector search capability.
• Practical experience with LLM applications: provider APIs and SDKs, RAG, tool calling, and prompt design.
• Deployment and operation on at least one major cloud (AWS, Azure or GCP), with Docker, Git and CI/CD.
• Observability and production support: structured logging, metrics, tracing, and root-cause analysis.
• Working knowledge of application security and reliability, including authentication, secrets management, and performance tuning.

Consulting and client engagement:

• Ability to understand business challenges and translate them into technical requirements.
• Clear communication with technical and non-technical stakeholders, including in workshops, technical discussions, and demonstrations.
• Comfort working embedded in a client team and building trust through accountability and delivery quality.

Good to have

• Agent orchestration and tool-calling frameworks (LangGraph, LangChain, OpenAI or Claude SDKs) and the Model Context Protocol (MCP). …