Senior AI Engineer — Generative AI & RAG

About the job

One of our clients is seeking a senior engineer to build production generative AI, retrieval and agent platforms.

Responsibilities

• Turn loosely defined business needs into scalable, dependable generative AI and machine-learning systems.
• Create reusable services, APIs, SDKs and platform building blocks for product engineering teams.
• Improve response time, throughput, scale, availability, output quality and operating cost.
• Own delivery from experimentation through launch, monitoring and production support.
• Develop agent orchestration covering planning, reasoning, memory and tool or function calls.
• Build shared capabilities for state, context, sessions, workflows and the lifecycle of single-agent and multi-agent applications.
• Evaluate LangGraph, LangChain and LlamaIndex, introducing reusable abstractions so teams do not rebuild the same foundations.
• Engineer the full retrieval pipeline, including ingestion, parsing, chunking, embeddings, indexing and retrieval.
• Implement semantic and contextual search with metadata filtering, ranking, reranking and context selection.
• Improve relevance, grounding, factual accuracy and performance through shared retrieval services.
• Develop evaluation frameworks for models, prompts, agents, retrieval components and complete applications.
• Automate benchmarks, comparison leaderboards, regression checks and experiment pipelines.
• Measure relevance, factuality, safety, latency, reliability and cost using offline, online and human evaluation.
• Compare model, prompt, retrieval and agent alternatives, and enforce quality gates before release.
• Manage model selection, routing, versions, configuration and lifecycle, alongside prompt versions, experiment tracking and deployment infrastructure.
• Introduce controlled releases using canaries, A/B experiments and rollback procedures.
• Instrument prompts, model calls, agent traces and retrieval with latency, error, token and cost monitoring; support alerts, debugging and incidents.
• Partner with infrastructure and security teams to make systems resilient and scalable.
• Embed responsible AI practices in the platform and its development process.
• Build reusable privacy, security, safety and policy controls against prompt injection, harmful output, sensitive-data disclosure and unsupported answers.
• Address bias, explainability, risk management and compliance requirements.
• Agree deployment standards with legal, privacy, security and responsible AI stakeholders.
• Set technical direction and architecture for significant AI initiatives spanning multiple teams.
• Shape the platform roadmap and strategy around consistent standards and reusable capabilities.
• Mentor data scientists, machine-learning engineers and software engineers through architecture, design and code reviews.
• Explain technical decisions clearly to engineering and business audiences.
• Align teams without relying on reporting authority, and encourage sound engineering, disciplined experiments and rigorous operations.

Required Qualifications

• A bachelor’s degree in computer science, AI, machine learning, statistics, mathematics, engineering or a related discipline, or equivalent practical experience.
• At least eight years developing and deploying production AI, machine-learning or data-driven systems.
• Strong Python skills, including data structures, algorithms, automated tests, APIs and system design.
• Experience designing and operating distributed systems, cloud services and microservices.
• Hands-on delivery of applications using large language models or foundation models.
• Practical experience with RAG, semantic search, embeddings and vector retrieval.
• Experience developing and evaluating agent systems.
• Experience building evaluation, experimentation and benchmarking frameworks.
• Experience deploying and monitoring machine-learning workloads in production.
• Strong written and verbal communication, with the ability to lead complex cross-functional work.