Senior AI Engineer (Applied AI / LLM & RAG)

About the role 

We are looking for a Senior AI Engineer to design, build and productionize enterprise-grade AI applications, with a strong focus on LLM-based solutions (commercial models), RAG pipelines, document automation, and integration with existing products and platforms. This role will complement a team with strong DevOps, fullstack and backend capabilities by bringing deep expertise in LLMOps, evaluation, AI architecture, and hands-on delivery of production AI systems operating under real-world traffic and reliability constraints. 

What you’ll do (responsibilities) 

Design and implement AI-powered features and applications (assistants, enterprise search, Q&A over documents, extraction/classification, workflow automation). 

Build robust integrations with commercial LLM APIs (e.g., Azure OpenAI/OpenAI) using Python, including streaming, function calling/tool use, error handling and cost controls. 

Architect and develop RAG end-to-end: embeddings and indexing (vector/hybrid search), retrieval, reranking, citations/grounding, “no-answer” patterns. 

Establish LLMOps practices: prompt/version management, automated evaluations and regression tests, tracing/observability, monitoring and alerting, deployment patterns and runbooks. 

Define and implement security & governance controls for enterprise environments: 

RBAC/ABAC and document-level permissions, PII handling (redaction/masking), 

mitigation of prompt injection and data exfiltration, auditability and compliance-ready logging. 

Provide technical leadership to full-stack developers by defining end-to-end AI architecture, set implementation patterns, and guiding delivery of production-ready services (CI/CD, secrets, scaling, reliability). Produce high-quality technical documentation and contribute reusable components/accelerators for faster delivery. 

What you’ll bring (minimum qualifications) 

Strong software engineering skills with Python (API development, clean code, testing). 

Experience integrating external APIs and building backend services (REST, auth, retries, rate limiting). 

Hands-on experience building LLM applications using commercial model APIs. 

Proven ability to provide technical leadership to full-stack developers, including designing end-to-end AI architecture and guiding implementation decisions. Hands-on experience deploying AI models and services to production environments, including operating under real-world traffic, performance, reliability, and monitoring requirements. 

Hands-on experience with Document AI, data ingestion pipelines, and unstructured data processing for document-centric automation use cases. 

Preferred qualifications 

Experience with Azure services (Azure OpenAI, Azure AI Search, Storage, Key Vault, Functions/App Service/Container Apps). 

Familiarity with frameworks such as LangChain / LlamaIndex / Semantic Kernel (or equivalent). 

Experience with hybrid search, reranking, evaluation frameworks, and observability (OpenTelemetry or similar). 

Experience with advanced AI architecture such as Multi-Agent Systems (MAS) or advanced approaches, including graph-based RAG.  

Prior work in regulated/enterprise environments and/or consulting delivery models. 

Key skills (summary) 

Python, FastAPI/Flask, testing (pytest), Git 

LLM APIs, prompt engineering, function calling/tool use 

RAG: chunking, embeddings, vector DB/search, hybrid retrieval, reranking, citations, grounding, evaluation.  

LLMOps: prompt/versioning, evaluation, monitoring, tracing 

Document AI, OCR, ingestion pipelines, unstructured data processing Security: PII, access control, prompt injection mitigations 

Architecture & leadership: end-to-end AI system design, technical guidance for full-stack teams  

Cloud & DevOps: Docker, CI/CD, logging/metrics, scalable deployment