About the Opportunity
We are partnering with an innovative technology company that is building next-generation AI solutions designed to transform complex, unstructured information into actionable business intelligence.
This is an opportunity to join a highly technical team focused on delivering production-grade AI systems that combine large language models, intelligent agents, knowledge retrieval, and enterprise software engineering.
We are looking for a Senior AI Platform Engineer who enjoys solving complex engineering challenges and building reliable AI-powered applications that users depend on every day.
⸻
The Role
As a Senior AI Platform Engineer, you will take ownership of the architecture and development of advanced AI services, including agent orchestration, retrieval-augmented generation (RAG), tool integration frameworks, and structured reasoning systems.
This is a hands-on engineering role rather than a research position. Success requires strong expertise in both modern AI application development and backend software engineering.
You will help design systems that are scalable, observable, cost-efficient, and robust enough for enterprise production environments.
⸻
What You'll Be Doing
Build Intelligent Agent Systems
- Design and implement multi-agent architectures capable of planning, execution, validation, and human-assisted decision-making.
- Develop complex workflows using LangGraph, LangChain, or custom orchestration frameworks.
- Create reliable tool-calling infrastructures that connect AI agents to external services and business systems.
- Develop memory and context-management strategies for long-running agent interactions.
Develop Advanced RAG Solutions
- Design and optimize retrieval-augmented generation pipelines.
- Work with vector databases and embedding technologies to improve knowledge retrieval performance.
- Implement advanced retrieval techniques including hybrid search, reranking, query decomposition, and citation-based grounding.
- Build scalable ingestion and indexing pipelines for large knowledge repositories.
Deliver Reliable AI Outputs
- Design systems that combine deterministic software logic with LLM-powered reasoning.
- Implement robust validation frameworks using Pydantic, JSON Schema, and structured output patterns.
- Create safeguards and quality controls that ensure consistent, production-ready outputs.
Drive AI Quality & Performance
- Develop testing and evaluation frameworks for AI-powered applications.
- Monitor quality, latency, cost, and user experience metrics.
- Build benchmarking, regression testing, and A/B testing capabilities.
- Optimize prompts, model selection strategies, caching, and token consumption.
Engineer Production-Ready Platforms
- Build and maintain APIs using FastAPI and modern Python frameworks.
- Implement real-time and streaming AI experiences.
- Work with PostgreSQL, Redis, Elasticsearch, and vector databases.
- Collaborate on containerized deployments using Docker and Kubernetes.
- Support the full software lifecycle from architecture through production operations.
⸻
What We're Looking For
Essential Skills & Experience
- 4+ years of professional software engineering experience.
- 2+ years building production AI or LLM-powered applications.
- Strong Python development skills with experience building scalable backend services.
- Hands-on experience with FastAPI or similar asynchronous web frameworks.
- Proven expertise in agentic AI frameworks such as LangGraph, LangChain, or custom orchestration systems.
- Experience designing and deploying RAG architectures.
- Deep understanding of prompt engineering, structured outputs, model selection, and LLM optimisation.
- Strong experience with Pydantic and schema-driven development.
- Solid database knowledge, including PostgreSQL and Redis.
- Experience working with vector databases such as Qdrant, Pinecone, Weaviate, FAISS, or pgvector.
- Experience building automated testing, monitoring, and evaluation systems for AI applications.
- Strong understanding of API design, WebSockets, and distributed systems.
- Excellent debugging and problem-solving skills.
⸻
Nice to Have
- Experience with Model Context Protocol (MCP).
- Knowledge of fine-tuning techniques such as LoRA or QLoRA.
- Experience building multi-tenant SaaS platforms.
- Familiarity with AI observability tools such as LangSmith or Langfuse.
- Experience implementing hybrid search solutions using Elasticsearch.
- Cloud platform experience, particularly AWS.
- Contributions to open-source AI projects or published technical work.
- Experience working on enterprise AI platforms or knowledge management systems.
⸻
Why This Opportunity?
- Work on cutting-edge agentic AI systems solving real business problems.
- Build production AI applications rather than experimental prototypes.
- Influence architecture and technical direction from an early stage.
- Collaborate with highly experienced engineers and AI specialists.
- Work with modern technologies across LLMs, agents, RAG, cloud infrastructure, and distributed systems.
- Join a company investing heavily in AI innovation and enterprise-scale platforms.
