Job description

Product Engineer | Fibr.ai

Bengaluru · In office

Stack: Python · FastAPI · Temporal · PostgreSQL · MongoDB · Redis

The role

Fibr is building the agentic web experience layer turning every URL into an intelligent agent that senses intent, makes decisions, and adapts in real time. Our agents personalise the full journey, running long LLM workflows against live customer accounts and millions of sessions.

You'll be a senior technical voice on the team shaping architecture, making the hard calls on system design, and owning the most complex parts of the platform. You'll work directly with the founding team and have real influence over where the product goes technically.

What you'll do

Own the hardest engineering problems durable workflows, eval infrastructure, agent reliability at scale
Set the technical direction for new surface areas agent architectures, data models, integration patterns
Ship AI-powered features end-to-end and hold the bar for quality across the team
Design systems that survive rate limits, partial failures, flaky third-party APIs, and real production load
Build the evals, guardrails, and instrumentation framework the whole team ships against
Sit at the table for architecture decisions and drive them forward
Mentor and raise the bar for the broader engineering team

Must-haves

2-3 years of production backend experience
Python is your primary language and we move fast
Has shipped LLM-powered features to real users at scale not demos, not side projects. Talk about what broke, how you debugged it, and what you rebuilt
Has designed and owned eval infrastructure for LLM systems show us the harness, the dataset, and how it drove ship/no-ship decisions
Has taken systems from 1 to 100 not just 0 to 1. You've dealt with scale, reliability, and production incidents firsthand
Deep experience with durable workflow systems in production Temporal, Celery, or similar at real scale
Strong system design fundamentals you think about failure modes before you write the first line
Strong product thinking alongside engineering depth you catch the product gap before the PM does
Asks clarifying questions before jumping into solutions you understand the problem before you build the solution
High ownership decisions are yours to make, not wait for

Nice-to-haves

Multi-agent architectures or complex tool-use pipelines in production
Experience with rate-limited third-party APIs at scale ad platforms, CRMs, analytics tools
Vector stores, RAG pipelines, or retrieval systems in production
LLM observability and tracing LangSmith, Langfuse, Prometheus, or similar
Time spent as a founding engineer or early engineer at a seed/Series A startup
Has mentored junior engineers or led technical decisions in a small team
Strong product sense you catch the system design issue and the UX issue

This role is not for you if:

Your AI experience is limited to personal projects or hackathons
You've only built demos or PoCs that never reached real users
You need detailed specs before you can start building
Your primary language is JavaScript or Java
You've only ever worked at large companies where someone else made the hard calls

How we work

High ownership, low bureaucracy. Decisions in the room, not in docs. You'll work directly with the founding team and have real influence over technical direction from day one.

Why Fibr AI

Direct technical influence at an Accel-backed AI startup
A chance to architect systems at the frontier of agentic AI

Someone shared one job with you. ASAI keeps finding the rest.

Scored, not searched. Every role ranked against your actual profile.

Alerts as often as hourly. Reach new roles while the pile is still small.

Skill gaps, spelled out. See exactly which requirements you don't meet yet.

Verified jobs, only. Say no to ghost jobs. Your time deserves respect.