Role Description A full-stack platform engineer who can run a multi-app B2B platform end to end — by directing fleets of AI agents and verifying everything in the real environment. You'll own the whole stack: cloud infrastructure, backend, frontend, data, and deep enterprise-ERP integration. The job isn't writing code with AI; it's operating it — decompose, fan out, verify adversarially, ship. One seat doing what's normally three or four. We run a B2B platform spanning roughly ten applications on a shared cloud backbone, with deep integration into customers' enterprise systems (SAP/ERP). This role owns it end to end — from the Terraform and IAM underneath to the React components on top, and the SAP RFC calls in between. The differentiator isn't typing speed. It's the ability to hold an entire platform in your head and conduct AI agents through it without dropping correctness — shipping across many repositories at once while keeping the architecture coherent. AI orchestration here is not a productivity add-on; it's the core multiplier that makes the scope possible. We hire for that fluency, and for the discipline that makes it safe. What You'll Do - Own the platform end to end. Multiple applications plus shared SDKs on a single cloud backbone — React/TypeScript front ends, FastAPI/Python services, the Terraform/IAM/ECS infrastructure underneath, and a shared design system. - Stand up infrastructure and environments from scratch. New services, cloud accounts, tenants, connectors, data syncs, migrations (including cross-region) — provisioned and proven, never just stood up and assumed. - Direct fleets of coding agents. Decompose a cross-repo change into disjoint tasks, fan them out to parallel agents in isolated worktrees, run adversarial multi-reviewer passes, then reconcile the results. - Integrate with enterprise systems at depth. SAP/ERP integration via RFC/BAPI — reading and where necessary authoring ABAP, reverse-engineering business rules, handling sales-order and customer-master flows, currency/unit/sales-area mapping, and idempotent event sync. - Architect multi-tenant data. Postgres row-level security as the tenant-isolation core, JSONB-backed tenant-extensible capability platforms (custom fields, validation, masking), careful migrations, and a graph database where it fits. - Ship at volume without losing coherence. Multiple PRs across multiple repos in a working session, CI green, deployed and verified — while keeping the design clean. - Author the thinking, not just the code. Specs, design docs, discovery-question sets, and runbooks that let work be understood and resumed by others. - Build the tooling that makes AI effective here. Per-codebase navigation maps, documentation indexes, guard hooks, and custom skills — invest in making agents good at this codebase, then reap it on every task after. - Automate yourself forward. Treat every repeated task as a bug to be fixed. When a workflow recurs, capture it as a reusable Claude skill, hook, or slash command so the next run — yours or a teammate's — is one step instead of ten. - Review like an adversary, deploy like a surgeon. Catch the regression the happy path missed, separate “it renders” from “the data is correct,” refute false blockers, and touch shared state only with a reason and a green light. How We Work - Hire for the disposition. The stack is learnable; this isn't. - Prove it in the real environment. “Done” means demonstrated, not asserted. - Never guess. Verify what's knowable in the code; ask about what's a genuine product decision; assume nothing in between. - Diagnose before you touch. “Look into it” means read-only until told to fix — especially on anything live. - Copy what works. If working examples already solve a problem, read the proven pattern and adapt it. - Enhance in place, never fork. Generalize the existing path — add an optional parameter where today is the degenerate case. - Risk isn't size. Bigger isn't worse; riskier is. - Build to scale — or name the debt. Ship the agreed slice now, but flag anything that won't scale as explicit, revisit-able debt. - Own the correction. Verify findings adversarially — a second pass whose job is to refute the first. - Words are a feature. Terminology has precise internal meaning. - Leave a trail. Every session ends with a handoff so the next one — human or agent — starts informed. Environment - Frontend — React, TypeScript, Vite, TanStack Query, vitest, a token-based design system, Playwright for verification. - Backend — Python, FastAPI (async), SQLAlchemy, Alembic, Celery, Pydantic; an SNS®SQS event bus with idempotent dedup. - Data — PostgreSQL with row-level security, schema-per-app, JSONB + GIN/GIST, Neo4j (Cypher), pgvector. - Platform / Infra — AWS (ECS Fargate, Aurora, RDS Proxy, Route53, ACM, WAF, CloudFront, IAM/OIDC), Terraform, dual-account, per-branch Docker stacks, gitflow. - Enterprise integration — SAP ECC via RFC/BAPI, ABAP, pyrfc, customer/order master data, additional ERP connectors, M2M auth. - Identity & AI — Auth0 (Organizations, M2M, custom claims), JWT entitlement gating; Claude Code agents, worktrees, skills, hooks, MCP. Must have - Fluent AI orchestration. You already run agents in parallel, isolate their work in worktrees, and verify their output adversarially. - Genuine full-stack + infra range. Comfortable going from a React component to a Postgres RLS policy to a Terraform module in the same day. - Systems debugging instinct. You chase root cause across service boundaries. - The evidence reflex. You distrust green badges, demand real fixtures, and prove things with a working screenshot, a read-back record, or a live payload. - Self-correction. You can describe a time you reversed your own confident conclusion because the evidence said so. - An automation reflex. You instinctively turn recurring work into reusable Claude skills, hooks, and commands. - Operating discipline. Read-only until authorized, copy proven patterns, enhance-in-place, precise language, clean handoffs. - Thick skin & plain speech. You take blunt, fast feedback well and explain your reasoning simply. Nice to have - Enterprise ERP / SAP depth. RFC/BAPI, ABAP, customer & order master data. - Tooling-builder streak. You've built the scaffolding that makes other agents and engineers effective. - Architectural taste under constraint. You reach for the boundary that keeps future cost flat. - Multi-tenant / B2B context. Tenancy isolation, per-tenant configuration, and the failure modes they bring. - Compliance fluency. GDPR / SOC 2 / ISO 27001 — comfortable with ROPA, control mappings, and runbooks. - Design-system literacy. Tokens over hardcoded values; able to run a UX and a UI pass on your own work.

• AI Product Development: Progetterai e implementerai feature basate sia su Generative AI (fine-tuning e orchestrazione di LLM come Llama o OpenAI) che su modelli di Machine Learning classico. • Bridge Tech-Business: Lavorerai a stretto contatto con il Product Team per identificare i casi d'uso ad alto impatto, traducendo i bisogni di business in progetti di data science concreti. • MLOps & Infrastructure: Non scriverai solo modelli, ma contribuirai a costruire l'infrastruttura per il prompt management, il monitoraggio dei modelli, l'ottimizzazione dei costi e le pipeline di deploy. • Continuous Improvement: Monitorerai le performance dei modelli in produzione, analizzando i dati di utilizzo per iterare e garantire che l'AI porti vero valore al business.

• Building and shipping generative AI features end to end: from model selection and fine-tuning through to the inference path that serves them. • Designing multi-agent and RAG architectures, and anomaly detection, that are accurate, observable, and cost-aware at scale. • Owning the real-time inference layer on Triton and TensorRT, optimising for latency, throughput, and GPU efficiency. • Standing up the surrounding microservices in Python and FastAPI, containerised and orchestrated for reliability. • Setting the technical bar: making architecture decisions, raising code quality, and mentoring engineers around you. • Partnering with research and product teams to take ideas from experiment to a service customers depend on.

Role Description Most engineers get to use large language models. You will get to build the systems that run them in production, at scale, under real latency and reliability constraints, for one of the most recognised names in application security and traffic management. Our client is expanding its AI Core group and is looking for a Senior or Staff AI & ML Engineer in the UK. This is hands-on, build-focused work at the centre of how the business turns generative AI from a prototype into a dependable product. You will design and ship multi-agent systems, retrieval-augmented generation pipelines, anomaly detection, fine-tuned models, and the real-time inference layer that serves them. If you want ownership over a serving stack rather than a single notebook, and you want your work measured by what holds up in production rather than what demos well, this is the seat. What you will own - Building and shipping generative AI features end to end: from model selection and fine-tuning through to the inference path that serves them. - Designing multi-agent and RAG architectures, and anomaly detection, that are accurate, observable, and cost-aware at scale. - Owning the real-time inference layer on Triton and TensorRT, optimising for latency, throughput, and GPU efficiency. - Standing up the surrounding microservices in Python and FastAPI, containerised and orchestrated for reliability. - Setting the technical bar: making architecture decisions, raising code quality, and mentoring engineers around you. - Partnering with research and product teams to take ideas from experiment to a service customers depend on. Qualifications - 5 to 10 years of relevant experience, including a proven track record as a technical lead who mentors others. - Strong, current Python engineering, with production services built and shipped (FastAPI or similar). - Genuine hands-on GenAI depth: LLMs, RAG, agentic or multi-agent workflows, anomaly detection, and fine-tuning (for example LoRA or PEFT). - Real-time inference experience with NVIDIA Triton and TensorRT, with real attention to latency, throughput, and cost. - A microservices mindset, with services built in Python and FastAPI, containerised and orchestrated for reliability. - Solid grounding in Docker and Kubernetes, and large-scale distributed systems on a major cloud. - Right to work in the UK. We welcome applications from all backgrounds and are committed to equal opportunity. Requirements - Experience with vLLM or other serving frameworks alongside Triton and TensorRT. - Experience in security, networking, or other high-reliability domains. - Big-data tooling (Spark, Databricks, Snowflake) and modern MLOps practice. Benefits - A genuine build mandate inside an established AI Core team, not a proof-of-concept that never ships. - Fully remote working anywhere in the UK, built around delivery rather than presence. - Competitive salary, strong benefits, and clear scope to grow into staff and principal-level influence. - The backing of C-Serv throughout: a delivery partner that runs a real quality filter and looks after its people, end to end. - A clear path to grow into staff and principal-level technical influence. - Full support from C-Serv across the hiring process and beyond, with full-cycle accountability. - A values-led, woman-owned delivery partner built on empathy, integrity, collaboration, and growth.