Senior AI Engineer, Agentic Systems
Career.io (TalentWW) · Remote
About this role
## Senior AI Engineer, Agentic Systems **Location:** Remote (Work from Home) **Employment Type:** Temporary to Full Time **Experience Level:** Tech Experienced --- ### About the Company Careerminds is a leader in career transition and coaching solutions, helping organizations support employees through change while enabling workforce growth and development. Their portfolio includes Career Transition and Coaching Services, plus **Progression**, an application for Career Frameworks and progression planning. --- ### The Role You’ll help build a **new AI career companion app** (separate from the main platform) in its early stages. At the core is: - A **conversational assistant** that supports users with their job search - An **agentic feature** that can take actions on the user’s behalf, such as: - Updating a resume - Searching for jobs - Preparing for interviews - Following up on outcomes Because the team is small and the direction is set, you’ll have significant ownership of key technical choices. --- ### Key Responsibilities **Conversation & Memory** - Build a multi-turn assistant that maintains context across sessions over weeks/months - Implement user memory & personalization (what they shared, what they’ve done, what changed) - Retrieval over the coaching corpus, with fine-tuning when beneficial - Conversation design: decide when to ask, suggest, act, or refer users elsewhere **Agent Orchestration** - Multi-step workflows with explicit state, tool calling, and handoffs between specialized agents - Determine when user confirmation is required vs. when actions can proceed automatically - Route between model providers based on cost/latency/quality, with fallbacks - Add traces for every agent decision so failures can be debugged **Evaluation & Experimentation** - Offline evaluation sets for multi-turn conversations - LLM-as-judge scoring validated against human ratings - Online experiments on live traffic, measured by user outcomes (applications, interviews, offers) **Safety & Compliance** - 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 Engineering** - Streaming responses and latency work - Cost per conversation optimization (caching, routing, prompt compression) - Deployment using FastAPI, async Python, Postgres, Redis, AWS --- ### Must-Haves - **5+ years** as a software or ML engineer, including **2+ years shipping LLM-based products** to real users - Experience building a **conversational product** used by real people (clear examples of what worked/what didn’t) - Production experience with **agent frameworks** (e.g., LangGraph), tool calling, MCP, structured outputs, and state management - Experience evaluating multi-turn systems (offline eval sets, judge validation, online testing) - Guardrails + adversarial input experience in a live product - Streaming, latency, and cost optimization for LLM systems - **Python**, async programming, and API design; plus Git, Docker, and AWS - Interest in the domain: careers, coaching, and how people make decisions about work --- ### Nice-to-Haves - Fine-tuning / post-training on conversational data (SFT, DPO, distillation) - Voice interfaces (STT, TTS) and real-time conversational agents - Consumer product experience - Background in coaching, education, health, or similar domains - MCP server development - Classical ML or recommendation sys
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.