Senior AI Solution Engineer

Gazelle Global; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

Gazelle Global is seeking a Senior AI Solution Engineer to partner with business stakeholders and transform ambiguous AI challenges into scalable, production-ready solutions. You will lead discovery, design the approach, develop code, and own deployment and production support for enterprise-grade AI apps.

You will build retrieval pipelines, AI agents, and scalable AI-powered applications with strong emphasis on governance, security, and cost efficiency across the organization.

Qualifications

• 10+ years of professional software engineering experience with Python proficiency.
• Experience building LLM-powered apps, including prompt engineering and evaluation.
• Experience designing end-to-end RAG pipelines and integrating LLM solutions.
• Strong system design, APIs, distributed systems, and cloud-native development.
• Ability to build evaluation frameworks and guardrails for non-deterministic systems.
• Excellent communication and ability to lead technical discovery.
• Experience in regulated industries / financial services.
• Experience with vector databases and LLM tooling.
• Experience with LangChain, LlamaIndex, or MCP.
• Experience with MLOps/LLMOps: monitoring, observability, CI/CD for ML/LLMs.
• Experience implementing Responsible AI and AI governance.

Responsibilities

• Partner with stakeholders to translate needs into technical requirements.
• Design, build, and operate production-grade generative AI apps.
• Architect and implement end-to-end RAG pipelines with embeddings and vectors.
• Develop AI agents and workflows with auditable guardrails.
• Define acceptance criteria and measure correctness and latency.
• Own the full solution lifecycle including observability and cost monitoring.
• Apply FinOps to AI workloads and manage token usage.
• Embed security, privacy, and compliance controls.
• Collaborate with InfoSec and Data Governance for compliance.
• Produce technical docs, runbooks, and architecture diagrams.
• Demonstrate full-stack capabilities from frontend to backend.

Skills

Python

LLM apps

Retrieval pipelines

Agent development

Evaluation frameworks

Production systems

Cloud-native

APIs

Distributed systems

Security and privacy

IAM

Encryption

Data governance

LangChain

LlamaIndex

MCP

MLOps/LLMOps

Guardrails

Observability

Mentoring engineers

Education

Bachelor's degree in Computer Science or Engineering

Tools

pgvector

Pinecone

Weaviate

Chroma

LangChain

LlamaIndex

MCP

Job description

As a Senior AI Solution Engineer, you partner with business stakeholders to transform ambiguous challenges into practical AI solutions that enhance investment processes and drive business outcomes.You serve as the critical bridge between business teams who own the problem and the AI platform that delivers the solution. You lead discovery sessions, define the solution approach, develop the code, and take ownership of deployment and production support. This is a hands-on engineering role that requires equal comfort collaborating with business teams in working sessions and building technical solutions such as retrieval pipelines, AI agents, and scalable AI-powered applications. You will play a key role in establishing best practices and setting the standard for how generative AI solutions are designed, deployed, governed, and operated responsibly at enterprise scale across the organization.

Your responsibilities:

• Partner directly with business stakeholders to understand workflows, identify high-valueopportunities, and translate ambiguous business needs into clear technical requirements
• Design, build, and operate production-grade generative AI applications, including copilots, assistants, knowledge-search platforms, and agentic workflow solutions, ensuring reliability and scalability beyond proof-of-concept implementations.
• Architect and implement end-to-end Retrieval-Augmented Generation (RAG) pipelines, including document parsing, data ingestion, chunking strategies, embeddings, vector databases, retrieval mechanisms, and prompt management.
• Develop AI agents and agentic workflows capable of planning and executing complex multi-step tasks within defined, auditable boundaries, supported by robust guardrails for safe and predictable behavior.
• Practice evaluation-driven development by defining acceptance criteria upfront, building evaluation frameworks, and measuring correctness, latency, and hallucination rates to ensure solution quality and prevent production regressions.
• Own the complete solution lifecycle, from discovery and design through development, deployment, and operational excellence, including observability, cost monitoring, and audit capabilities to proactively identify performance degradation
• Apply FinOps and cost-optimization practices to AI workloads by tracking and managing token usage, inference costs, and infrastructure spend to ensure solutions remain cost-effective as they scale.
• Apply responsible AI principles and risk-based judgment appropriate to each use case, collaborating with risk and compliance teams to establish controls, human oversight mechanisms, and audit trails that enable rapid and safe adoption of AI solutions
• Embed security, privacy, and compliance controls into solution architectures, including Identity and Access Management (IAM), encryption, and audit logging
• Partner with Information Security (InfoSec) and Data Governance teams to ensure compliance with regulatory requirements and internal policies, including SOC 2 and applicable data privacy regulations
• Develop reusable tools, frameworks, patterns, and playbooks, and share insights with platform, product, and engineering teams to accelerate organizational learning and execution.
• Produce clear technical documentation, operational runbooks, and architectural diagrams that enable teams to understand, maintain, operate, and extend the solutions being built.
• Demonstrate full-stack engineering capabilities across development environments, supporting end-to-end solution delivery from front-end interfaces to back-end services and infrastructure.

Your Profile

• 10+ years of professional software engineering experience, with strong proficiency in Python (or a comparable modern language).
• Hands-on production experience building and shipping LLM-powered applications, including advanced prompt engineering, retrieval, agent development, and evaluation.
• Demonstrated experience designing and building end-to-end RAG pipelines and integrating LLM solutions with real systems.
• Strong understanding of system design, APIs, distributed systems concepts, and cloud-native development, with a track record of owning production systems built on solid architectural foundations.
• A disciplined approach to evaluation and testing for non-deterministic systems. Ability to build evaluation frameworks and guardrails as a core part of the development lifecycle.
• Strong communication skills with the ability to lead technical discovery, write clearly, and convey technical concepts to diverse audiences while maintaining a collaborative approach.
• High level of ownership and comfort navigating ambiguity within large, regulated organizations, making sound trade-offs between scope, speed, and quality.
• Bachelor's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
• Experience implementing security, privacy, and compliance controls in production environments, including IAM, encryption audit logging, and data governance practices, ideally within regulated industries.
• Background in financial services or another regulated enterprise environment.
• Experience with vector databases such as pgvector, Pinecone, Weaviate, or Chroma.
• Experience with agent and orchestration frameworks such as LangChain, LlamaIndex, or Model Context Protocol (MCP).
• Experience with MLOps/LLMOps tooling, including experiment tracking, model versioning, monitoring, evaluation, observability, and CI/CD pipelines for ML and LLM systems.
• Experience implementing Responsible AI and AI governance controls, including guardrails, human-in-the-loop oversight, and audit trails.
• Experience mentoring engineers and defining technical standards as a senior individual contributor.