Note: The job is a remote job and is open to candidates in USA. Careerminds provides career transition, coaching, and career progression solutions that support organizations and employees through workplace change and development. The Senior AI Engineer will lead the technical development of an early-stage AI career companion, building conversational assistance, agentic workflows, evaluation systems, safety controls, and production infrastructure.
Responsibilities
- 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
- 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
- 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)
- 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
- Streaming responses and latency work
- Cost per conversation: caching, routing, prompt compression
- Deployment: FastAPI, async Python, Postgres, Redis, AWS
Skills
- 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, and AWS
- Interest in the problem domain: careers, coaching, how people make decisions about work
- 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
Benefits
- 100% remote/work-from-home role
Company Overview
Company H1B Sponsorship