← Back to Jobs
AI Engineer, Senior Associate
London
1 month ago
💻 Open SourceUses AI-assisted coding tools like Cursor and Windsurf and explicitly calls out reducing 'vibe coding' through rigorous human review and production standards.
About the Role
Senior Associate AI Engineer responsible for end-to-end delivery of AI features in London, including building RAG pipelines, cleaning and engineering data, integrating LLMs, and shipping reliable production APIs. The role blends data engineering, model/product thinking, agentic workflows, and security/governance for production AI systems.
Job Description
Role
We are hiring an AI Engineer (Senior Associate) to own end-to-end delivery of AI features: from ingesting and cleaning unstructured data, to building and operating RAG pipelines, integrating LLMs, designing agentic workflows, and shipping well-tested backend APIs into production. The role sits between research and engineering and emphasizes production reliability, security, and product thinking.
Key Responsibilities
- Design, build, and maintain Retrieval-Augmented Generation (RAG) pipelines over unstructured data (PDFs, HTML, emails, transcripts, APIs) using embeddings, vector databases and graph databases.
- Implement and tune chunking strategies and retrieval techniques to preserve context and improve quality.
- Integrate LLMs (OpenAI, Anthropic, open-source) via SDKs/HTTP and handle context windows, rate limits, retries, timeouts, and graceful degradation.
- Design multi-agent / agentic workflows, handle conversation state management, tool routing, and agent hand-offs.
- Implement security and governance controls (prompt-injection defenses, output filtering, role/permissioning, data privacy/GDPR/SOC2 awareness).
- Fine-tune or adapt open-source models and manage training/inference pipelines; experiment with architectures and hosted APIs.
- Build ETL jobs and ingestion scripts to clean, normalize, and enrich text data; work with SQL and vector stores.
- Own prompt design, evaluation, and regression testing for AI features, and monitor/diagnose production behavior (hallucinations, latency, accuracy).
- Build and maintain typed, tested backend services exposing AI capabilities (APIs/microservices) and implement observability (logging, metrics, tracing, token usage).
- Collaborate with product, design, and ops, and take end-to-end ownership from prototype to production and continuous improvement.
Requirements
Technical
- Approximately 3+ years professional software engineering experience, including ~1–2 years building production AI/ML or LLM-based systems (non-traditional equivalents considered).
- Expert proficiency in Python for backend and data work (typing, async, packaging, testing, profiling).
- Hands-on experience with at least one orchestration framework (e.g., LangChain, LlamaIndex).
- Practical experience implementing RAG with embeddings and vector databases (e.g., Pinecone, Weaviate, Milvus, Qdrant) and semantic search.
- Comfortable using Graph DBs (PuppyGraph, Neo4J, TigerGraph, ArangoDB) and SQL; experience with pandas/BeautifulSoup or equivalents for preprocessing.
- Experience building and deploying APIs/microservices (REST, JSON, auth, rate limiting, pagination, error handling).
- Familiarity with software engineering fundamentals: testing, code reviews, version control (Git), CI/CD, and basic cloud services (AWS/GCP/Azure).
- Experience with Azure AI tools; nice-to-have: Microsoft Power Platform (Power Automate, Power Apps, Dataverse), Azure Logic Apps.
- Nice-to-have: experience with IAC tools (Terraform, Crossplane), AI infrastructure for scalable serving, distributed training, GPU orchestration, and knowledge of MCP.
AI/ML Understanding & Soft Skills
- Working understanding of LLM behavior: context windows, tokens, temperature/top-p, hallucinations, prompt injection risks, embeddings, vector similarity, and Transformer concepts.
- Experience shipping production AI features (e.g., RAG chatbots, summarization/search assistants, agentic workflows); portfolio or GitHub preferred.
- Strong problem-solving, product thinking, experimentation mindset, and ability to explain AI concepts to stakeholders.
- AI scepticism: verify AI outputs, design guardrails, and apply rigorous human review.
Benefits
- Private medical and life insurance
- Income protection
- Pension contributions
- Wellness benefits via partner organisations
- Volunteer day and global philanthropy program
- Professional development and career progression opportunities
- Competitive compensation, flexible “results-focused” working model, and social events
Location & Contact
- Location: London
- To apply: send CV and cover letter to [email protected] with subject “AI Engineer, Senior Associate, London”. Further information at www.partners-cap.com