ai engineer for career coaching

Careerminds provides career transition and coaching solutions that help organizations support employees through change and enable workforce growth and development. Its product portfolio includes Career Transition and Coaching Services and Progression, an application for career frameworks and progression planning.

• Build a multi-turn assistant that maintains context across sessions over weeks or months;
• Implement user memory and personalization;
• Develop retrieval over the coaching corpus and fine-tuning where valuable;
• Design when the assistant should ask, suggest, act, or refer users elsewhere;
• Build multi-step workflows with explicit state, tool calling, and handoffs between specialized agents;
• Decide which actions require user confirmation;
• Route between model providers based on cost, latency, and quality, with fallbacks;
• Add traces for every agent decision to support debugging;
• Create offline evaluation sets for multi-turn conversations;
• Implement LLM-as-judge scoring and validate it against human ratings;
• Run online experiments on live traffic and measure user outcomes;
• Build guardrails for scope, tone, and escalation in a consumer product;
• Handle prompt injection and jailbreaks;
• Design for GDPR and EU AI Act compliance;
• Implement streaming responses and latency improvements;
• Optimize cost per conversation through caching, routing, and prompt compression;
• Deploy services using FastAPI, async Python, Postgres, Redis, and AWS.

• 5+ Years of experience as a software or ML engineer, including at least 2 years shipping LLM-based products to real users;
• Experience building a conversational product used by people, with a clear account of what worked and what did not;
• Production experience with agent frameworks such as LangGraph or similar, tool calling, MCP, structured outputs, and state management;
• Experience evaluating multi-turn systems through offline evaluation sets, judge validation, and online testing;
• Experience with guardrails and adversarial input in a live product;
• Experience with streaming, latency, and cost optimization for LLM systems;
• Proficiency in Python, asynchronous programming, API design, Git, Docker, and AWS;
• Interest in careers, coaching, and how people make decisions about work;
• Nice to have: Fine-tuning or post-training on conversational data (SFT, DPO, distillation), voice interfaces (STT, TTS, real-time conversational agents), consumer product experience, background in coaching, education, health or similar, MCP server development, classical ML or recommendation systems.

• 100% Remote/work-from-home role;
• Temporary employment with a 6 month temporary-to-permanent arrangement;
• No conditions specified.