TS
Lead / Staff AI Agent Engineer
Tellus Solutions
- 🌏 Worldwide
- Remote
- Staff / Principal
- 4 hours ago
- AI
- Python
- TypeScript
- MCP
- LangGraph
- RAG
- OpenAI
- Kubernetes
- Slurm
- AIOps
- Incident Response
4 hours ago
- Client builds next-generation compute infrastructure for frontier AI, from pilot racks to hyperscale GPU clusters.
- We are hiring a hands-on Lead AI Agent Engineer to design, build and ship production agentic systems. You will join early, set technical direction for agent work, and may guide other engineers while staying an individual contributor.
Responsibilities:
- Design and build LLM-powered agents that plan, call tools and act reliably in production.
- Own agent architecture end to end: orchestration, tool and API integration, memory and retrieval, guardrails and human-in-the-loop controls.
- Build evaluation harnesses, test suites and observability so agent behavior is measurable and safe.
- Integrate agents with real systems such as infrastructure telemetry, ticketing, APIs and internal data.
- Make model and platform trade-offs on cost, latency and accuracy across frontier and open-weight models.
- Set engineering standards, review code and mentor engineers on agent best practices.
- Ship quickly in short cycles; show clear delivery within the first 90 days.
Skills:
- 8+ years of software engineering, with 2+ years building LLM applications or agents in production.
- Strong Python and/or TypeScript; solid backend and distributed systems fundamentals.
- Hands-on experience with agent tooling such as tool/function calling, MCP, LangGraph or similar orchestration, and retrieval (RAG, vector databases).
- Experience with frontier model APIs (Anthropic, OpenAI, Google) and with evaluating and hardening agent behavior.
- A track record at a well-run engineering organization with strong design review, testing and on-call practices.
- Ownership mindset: you take accountability for outcomes, communicate early and can be trusted with critical systems.
- Genuine interest in the mission of building infrastructure for frontier AI.
Nice to have
- Experience with AI infrastructure, HPC or data center systems (GPU clusters, Kubernetes, Slurm, DCIM, observability).
- Agents for operations: AIOps, incident response, or infrastructure automation.
- Experience at a frontier AI lab or an agent-first company.
- Tech lead experience on a small team.
Lead / Staff AI Agent Engineer · Tellus Solutions