Senior AI Engineer

Overview

Role Summary

Key Responsib

*Agentic AI & Multi-Agent Orches*

• tration
• Design and implement multi-agent systems where specialised agents collaborate on complex tasks: planning agents, execution agents, validation agents, and human-in-the-loop review steps
• Build agentic workflows using LangGraph, LangChain, or custom state machines with clear state management, conditional routing, retry logic, and graceful failure handling
• Implement tool-calling infrastructure: define tool schemas, manage tool registries, handle tool execution with timeouts and error recovery
• Design context management strategies for long-running agent sessions: conversation memory, working memory, context window optimisation, token budget management, and multi-turn state t
• *racking*

*RAG & Knowledge R*

• etrieval
• Build and optimise retrieval-augmented generation (RAG) pipelines: document chunking strategies, embedding model selection, vector store management (FAISS, Qdrant, pgvector, Pinecone), and hybrid search
• Implement advanced RAG patterns: multi-hop reasoning, reranking, query decomposition, self-querying retrieval, and citation grounding
• Design and maintain knowledge indexing pipelines that ingest, transform, and index domain-specific data
• *at scale*

*Deterministic Workflows & Structur*

• ed Output
• Design deterministic workflows that guarantee consistent, reliable outputsfrom LLMs
• Implement comprehensive input/output validation using Pydantic models, JSON Schema constraints, and structured output parsing
• Build hybrid pipelines combining deterministic business logic with LLM-powered
• *reasoning*

*Evaluation, Testing & Op*

• timisation
• Build evaluation frameworks for LLM-powered features: automated test suites, regression benchmarks, and continuous production monitoring
• Implement token optimisation strategies: prompt compression, caching, response streaming, batching, and model selection
• Design A/B testing infrastructure for prompt variants, model versions, and pipeline conf
• *igurations*
• *Platform & Application*

Development

• Build production APIs using FastAPI: endpoint design, async handlers, WebSocket/SSE for streaming responses, and graceful degradation
• Design and implement MCP (Model Context Protocol) server setups for standardised tool integration
• Work with PostgreSQL, Redis, and Elasticsearch for application state, caching, and search
• Containerise AI services with Docker and collaborate with DevOps on Kubernetes deployment
• and scaling

Required Qualifications

• 4+ years of software engineering experience, with at least 2 years focused on LLM-powered application developmentin production
• Strong proficiency in Python; experience with FastAPI or similar async frameworks required
• Deep hands-on experience with agentic AI frameworks: LangGraph, LangChain, or custom agent architectures
• Proven experience building RAG systems: embedding pipelines, vector databases, retrieval strategies, and multi-hop reasoning
• Strong understanding of LLM fundamentals: prompting, structured output, token management, and model selection trade-offs
• Working knowledge of PostgreSQL, Redis, and at least one vector database
• Experience with evaluation and testing of LLM outputs in production environments
• Solid understanding of REST APIs, WebSockets, and API lifecycle management

Preferred Experience

• Experience with MCP architecture: building MCP servers and integrating external systems
• as agent tools
• Familiarity with parameter-efficient fine-tuning methods (LoRA, QLoRA)
• Experience building multi-tenant AI applications with organisation-
• level isolation
• LLM observability experience: tracing, token usage tracking, latency profiling
• Familiarity with Elasticsearch and hybrid search(BM25 + vector)
• Cloud deployment experience (AWS preferred): EKS,S3, SQS, Lambda
• Contributions to open-source AI/LLM projects or published work in NLP or agentic AI