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. This is also a 6 month temporary to permanent role. THE KEY RESPONSIBILITIES Conversation and Memory A multi-turn assistant that maintains context across sessions over weeks or monthsUser memory and personalisation: what someone has shared, what they've done so far, what's changedRetrieval over the coaching corpus, and fine-tuning if it turns out to be worth itConversation design: when the assistant should ask, suggest, act, or refer the user elsewhereAgent Orchestration Multi-step workflows with explicit state, tool calling and handoffs between specialized agentsDeciding which actions need user confirmation and which don'tRouting between model providers based on cost, latency and quality, with fallbacksTraces for every agent decision so failures can be debuggedEvaluation Offline evaluation sets for multi-turn conversationsLLM-as-judge scoring, validated against human ratingsOnline experiments on live traffic, measured against user outcomes (applications, interviews, offers)SafetyGuardrails for scope, tone and escalation in a consumer productPrompt injection and jailbreak handlingGDPR and EU AI Act compliance as part of the designProduction Streaming responses and latency workCost per conversation: caching, routing, prompt compressionDeployment: 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 usersExperience building a conversational product that people used, and a clear account of what worked and what didn'tProduction experience with agent frameworks (LangGraph or similar), tool calling, MCP, structured outputs, state managementExperience evaluating multi-turn systems: offline eval sets, judge validation, online testingExperience with guardrails and adversarial input in a live productExperience with streaming, latency and cost optimisation for LLM systemsPython, asynchronous programming, and API design; Git, Docker, and AWS.Interest in the problem domain: careers, coaching, how people make decisions about work THE NICE-TO-HAVES Fine-tuning or post-training on conversational data (SFT, DPO, distillation)Voice interfaces: STT, TTS, real-time conversational agentsConsumer product experienceBackground in coaching, education, health or similarMCP server developmentClassical ML or recommendation systems At Careerminds, we believe that diversity in thought and cultural background leads to better teams and stronger companies. We seek talented, qualified employees, regardless of race, color, sex/gender (including pregnancy, gender identity, and gender expression), national origin, religion, sexual orientation, disability, age, marital status, citizen status, veteran status, or any other protected classification under country or local law. Careerminds is proud to be an Equal Employment Opportunity Employer. Come join our team. Together, we’ll help others tell their career stories and land their dream jobs.