Senior AI Engineer, Agentic Systems

**THE COMPANY** Careerminds is a leader in career transition and coaching solutions, helping organizations support employees through change while enabling workforce growth and development. Our product portfolio includes market\-leading Career Transition and Coaching Services as well as Progression, our application for Career Frameworks and progression planning. **THE ROLE** We are developing a new product, an AI career companion app. It is distinct from our main platform and is in its early stages. At its heart is a conversational assistant which helps people with their job search, along with an agentic feature that enables it to carry out actions on their behalf such as updating a resume, searching for jobs, preparing for an interview, and following up on the outcome. You would have control of that core since the team is small and the direction has already been decided, most of the technical choices being yours. This is a 100% remote/work\-from\-home role. **THE KEY RESPONSIBILITIES** *Conversation and Memory* * A multi\-turn assistant that maintains context across sessions over weeks or months * User memory and personalisation: what someone has shared, what they've done so far, what's changed * Retrieval over the coaching corpus, and fine\-tuning if it turns out to be worth it * Conversation design: when the assistant should ask, suggest, act, or refer the user elsewhere *Agent Orchestration* * Multi\-step workflows with explicit state, tool calling and handoffs between specialized agents * Deciding which actions need user confirmation and which don't * Routing between model providers based on cost, latency and quality, with fallbacks * Traces for every agent decision so failures can be debugged *Evaluation* * Offline evaluation sets for multi\-turn conversations * LLM\-as\-judge scoring, validated against human ratings * Online experiments on live traffic, measured against user outcomes (applications, interviews, offers) *Safety* * Guardrails for scope, tone and escalation in a consumer product * Prompt injection and jailbreak handling * GDPR and EU AI Act compliance as part of the design *Production* * Streaming responses and latency work * Cost per conversation: caching, routing, prompt compression * Deployment: FastAPI, async Python, Postgres, Redis, AWS **THE MUST\-HAVES** * 5\+ years as a software or ML engineer, including at least 2 years shipping LLM\-based products to real users * Experience building a conversational product that people used, and a clear account of what worked and what didn't * Production experience with agent frameworks (LangGraph or similar), tool calling, MCP, structured outputs, state management * Experience evaluating multi\-turn systems: offline eval sets, judge validation, online testing * Experience with guardrails and adversarial input in a live product * Experience with streaming, latency and cost optimisation for LLM systems * Python, asynchronous programming, and API design; Git, Docker,