Senior AI Engineer — Inference & Agent Systems
BengaluruFull-timeSenior levelPosted open since mar 2026
Senior data science role at Arcana Analytics in Bengaluru.
About the role
The problems here don't have blog posts about them yet. Parallel agent DAG execution under hard latency budgets, streaming synthesis across partial sub-agent results, eval harnesses for non-deterministic multi-step systems: these are genuinely unsolved at production quality. Every engineer's decisions ship to production.
What you'll do
- Drive TTFT below 400ms for multi-step agent pipelines
- KV cache strategy, prompt compression, dynamic context window management
- Design and implement Plan-Execute-Synthesize pipelines that run sub-agents in parallel DAGs, not sequential chains
- Build reliable orchestration on top of Temporal: retries, timeouts, partial failure recovery, idempotency
- Own the eval framework end to end: ground truth datasets, automated scoring pipelines, regression detection on every PR
What you need
- Machine learning
- LLMs
- Python
- Kafka
- PostgreSQL
- Go
Good to have
- Docker
- Regression testing
- Test cases