Senior AI Engineer

Arcana; Bengaluru; Hybrid; INR 1,500,000 - 2,500,000; Full time

Job summary

Arcana is seeking a Senior AI Engineer to enhance its AI agent systems. You will optimize inference pipelines, focusing on driving tight latencies while ensuring high reliability. This role requires hands-on experience with streaming LLMs and resilience engineering. Collaborating in a small team, you will be at the forefront of solving real-time AI challenges where production quality matters. The company values depth over breadth in technology familiarity, using tools like Go, Python, and Temporal.

Qualifications

• Experience optimizing inference pipelines for multi-step agent systems.
• Ability to debug complex LLM behaviors in production.
• Familiarity with asynchronous work architectures and observability practices.

Responsibilities

• Optimize TTFT for multi-step agent pipelines.
• Build and maintain an eval framework for regression testing.
• Implement orchestration for reliable execution of inference agents.

Skills

Inference optimization

Streaming LLM responses

Ground truth dataset creation

Debugging LLM non-determinism

Parallel sub-agent execution

Tools

Go

Python

Temporal

Kafka

PostgreSQL

Docker

Job description

Title: Senior AI Engineer — Inference & Agent Systems

Location: BLR/Remote India

What We're Building

Arcana is building AI agents that synthesize information across heterogeneous sources and deliver structured, reasoned answers in real time. The product only works if the agents are fast, reliable, and correct, not approximately correct.

Our stack: Go + Temporal for orchestration, a Plan‑Execute‑Synthesize agent architecture, and an evaluation harness we use to measure every regression. The problems are hard. The latency bar is aggressive. The accuracy requirements are unforgiving.

The Work

Inference Optimization

• Drive TTFT below 400ms for multi‑step agent pipelines
• Streaming optimization: first token to user while sub‑agents are still running
• KV cache strategy, prompt compression, dynamic context window management
• Multi‑provider routing: model selection by latency, cost, and task type across OpenAI, Anthropic, Gemini, and open‑weight models
• 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
• Structured output enforcement: JSON schema validation, retry loops on malformed LLM output, graceful degradation
• Tool call design: schema design that LLMs actually follow reliably across providers
• Own the eval framework end to end: ground truth datasets, automated scoring pipelines, 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 optimization
• Async worker architecture for parallel sub‑agent execution
• Observability: trace every token, every tool call, every synthesis step

What We're Looking For

Strong signal

• You have worked on inference pipelines where TTFT was the primary metric and you moved it meaningfully
• You have built multi‑step agent systems and you know where they break not from reading papers but from watching them fail in production
• You have written eval harnesses from scratch and you have opinions about what makes a ground truth dataset actually useful
• You have debugged LLM non‑determinism in production and built systems resilient to it
• You have worked with streaming LLM responses and built infrastructure around partial output handling

Weaker signal (but not disqualifying)

• You have fine‑tuned models but haven't shipped inference systems
• You have used LangChain/LlamaIndex but haven't built the layer underneath
• Strong ML research background without systems exposure

Stack familiarity

We care more about depth than match: Go, Python, Temporal, Kafka, PostgreSQL, Docker.

Why This 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. Small team. High ownership. Every engineer's decisions ship to production.

Who We Want to Hear From

• You’ve shipped inference systems at a real‑time AI product (search, coding assistant, chat at scale)
• You’ve built an agent platform in any domain
• Or you’ve built eval/harness infrastructure that a team of 10+ engineers actually trusted to catch regressions