Forward Deployed Engineer – LLMOps

About the role

The Forward Deployed Engineer – LLMOps will own the production operations for large‑language‑model (LLM) and agentic workloads. You will ensure reliable serving, cost efficiency, and observability for systems that are far less predictable than traditional machine‑learning pipelines.

Key responsibilities

• Operate and scale inference infrastructure for LLM/agentic workloads, including load balancing and caching.
• Monitor and control token‑based inference costs, optimizing routing and batching strategies.
• Build observability for LLM‑specific failure modes such as hallucination, latency spikes, and prompt drift.
• Manage model version rollouts using canary releases, fallback models, and A/B testing.
• Lead incident response for production issues affecting client‑facing systems.
• Collaborate with GenAI Engineers and Agentic AI Architects on production‑readiness reviews.
• Explain token‑cost dynamics to finance and business stakeholders.

Required profile

• 4–6 years of platform/MLOps engineering experience with hands‑on LLM/GenAI production.
• Deep understanding of LLM inference economics, including token costs, batching, caching, and model routing.
• Experience building canary/rollback strategies for probabilistic systems.
• Ability to stay calm under pressure during live incidents.
• Strong communication skills to convey cost implications to non‑technical stakeholders.

Required skills

• AWS Bedrock
• Microsoft Azure AI Foundry
• Google Vertex AI
• vLLM
• TGI
• LLM inference economics
• LLM observability tooling (tracing, eval pipelines, prompt/version management)