About the role
The candidate will have responsibilities across the following functions:
Inference Optimisation:
- Drive TTFT below 400ms for multi-step agent pipelines.
- Streaming optimisation: first token to user while sub-agents are still running.
- KV cache strategy, prompt compression, and dynamic context window management.
- Multi-provider routing: model selection by latency, cost, and task type across OpenAI, Anthropic, Gemini, and open-weight models.
Agent Architecture:
- Design and implement Plan-Execute-Synthesise pipelines that run sub-agents in parallel DAGs, not sequential chains.
- Build reliable orchestration on top of Temporal: retries, timeouts, partial failure recovery, and idempotency.
- Structured output enforcement: JSON schema validation, retry loops on malformed LLM output, and graceful degradation.
- Tool call design: schema design that LLMs actually follow reliably across providers.
Evaluation and Harness:
- Own the eval framework end to end: ground truth datasets, automated scoring pipelines, and regression detection on every PR.
- LLM-as-judge pipelines for qualitative output assessment.
- Latency regression testing - p50/p95/p99 tracked across every deployment.
- Adversarial test case design: ambiguous queries, missing data, conflicting sources, malformed tool responses.
Infrastructure:
- Model serving and cold start optimisation.
- Async worker architecture for parallel sub-agent execution.
- Observability: trace every token, every tool call, every synthesis step.