Forward Deployed Engineer

Revrag Ai

Bengaluru

On-site

INR 900,000 - 1,500,000

Full time

12 days ago

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

RevRag AI, a Bengaluru-based deep-tech startup, seeks a Forward Deployed Engineer to build and deploy Voice and In-App AI Agents for clients. You will configure deployments, write prompts, wire tools and guardrails, and work with customer teams to go live.

In this role you’ll own end-to-end deployments, iterate on prompts to improve agent accuracy and latency, integrate with client systems via APIs and SDKs, and help scale playbooks. Travel to client sites may be required.

Qualifications

2–3+ years building and shipping production software.
Hands-on experience with LLM/GenAI apps, prompting and tool calling in production or customer settings.
Comfortable in fast-paced, customer-facing environments.

Responsibilities

Build and deliver customer deployments: configure Voice and In-App AI Agents, wire up tools and guardrails, and take them from setup through go-live.
Write, iterate, and tune prompts and conversation design for the agents, including multilingual and edge‑case handling, and measure quality with evaluations.
Integrate agents with customer systems via APIs, SDKs, and telephony.
Run evaluations and help improve agent accuracy, latency, and conversion.
Debug production issues and improve reliability and quality.
Prepare and support demos and walkthroughs for customer stakeholders.
Work closely with senior FDEs, product, and engineering; document deployments and contribute to reusable playbooks.
May occasionally travel to or work from client sites to support deployments and help ensure smooth operations.

Skills

LLM/GenAI applications

Prompt engineering

Customer-facing experience

Ownership & fast-learning

Tools

Python

APIs & Webhooks

SDK integration

AWS cloud

Job description

About the role

We’re looking for a Forward Deployed Engineer who loves building, shipping, and tuning AI agents and working closely with customers to take our Voice and In-App AI Agents into production.

This is a hands‑on, customer‑facing engineering role.

You’ll build and deliver customer deployments: configuring agents, writing and iterating prompts and conversation flows, wiring up tools and guardrails, integrating with client systems, and running evaluations, working alongside senior FDEs and core engineering.

You’ll learn fast, take ownership of your work, and grow into owning deployments end to end.

Key Responsibilities

Build and deliver customer deployments: configure Voice and In-App AI Agents, wire up tools and guardrails, and take them from setup through go-live.
Write, iterate, and tune prompts and conversation design for the agents, including multilingual and edge‑case handling, and measure quality with evaluations.
Integrate agents with customer systems via APIs, SDKs, and telephony.
Run evaluations and help improve agent accuracy, latency, and conversion.
Debug production issues and improve reliability and quality.
Prepare and support demos and walkthroughs for customer stakeholders.
Work closely with senior FDEs, product, and engineering; document deployments and contribute to reusable playbooks.
May occasionally travel to or work from client sites to support deployments and help ensure smooth operations.

Experience

2-3+ years building and shipping production software.
Hands‑on experience with LLM and GenAI applications (prompting, RAG, tool calling), ideally in production or real customer settings.
Comfort working in fast‑paced environments with ownership of your work; customer‑facing exposure is a plus.

Technical Skills

Solid Python and good software engineering fundamentals.
Practical prompt engineering for LLM agents (system prompts, tool use, structured outputs), and eagerness to go deep on it.
Working knowledge of LLM application development.
Understanding of APIs, webhooks, and SDK integration.
Some experience with cloud platforms (AWS preferred); willingness to debug production and learn reliability and latency fundamentals.
Good written and verbal communication, comfortable in customer conversations and demos.

What Were Looking For

Ship quickly and iterate, and enjoy crafting prompts and agent behaviour until they work reliably in production.
Are comfortable talking to customers and translating needs into working configurations.
Take ownership of your work end to end.
Are curious and a fast learner, and thrive in a fast‑changing environment.
Care about quality and customer success.

Success in This Role

Reliably deliver your deployments on time and with quality.
Write prompts and configurations that hold up in production.
Grow into owning deployments end to end.
Contribute playbooks and improvements back to the team.
Build trust with customers and teammates.

Bonus Points

Exposure to Voice AI systems
LiveKit Agents, Pipecat, or WebRTC
Telephony integrations
Prompt engineering or conversation design for chatbots or agents
BFSI, fintech, or insurtech domain exposure
Indian language and multilingual systems
Building AI or automation projects end to end

About RevRag AI

RevRag AI is a Bengaluru‑based deep‑tech startup building production‑grade Voice AI and LLM‑powered automation for customer‑facing workflows. Our multilingual, in‑app AI agents plug directly into BFSI journeys, improving digital onboarding, sales, and support while cutting operational cost by up to 70%.

We work with leading BFSI organisations including Mahindra Finance, Motilal Oswal, PayTM Insurance, PhonePe, KreditBee, Razorpay, Udaan Capital, Kissht, PolicyBazaar, InsuranceDekho, Open Capital, and EaseBuzz.

Contact

US Office

8 The Green Dover,
DE 19901, USA

India Office

HSR Layout, Bengaluru,
Karnataka 560102

Empowering Financial Apps to
Scale Smarter, Faster, Better!

ISO Certified

RevRag AI utilizes real‑time APIs to fetch the information you need. Your data remains securely in its original location while we provide seamless access across our platform.

SOC 2 Compliance:

RevRag AI is aligned with globally recognized SOC 2 standards, guaranteeing exceptional data security and management practices.

Role‑Based Access Control

Our platform adheres to the highest standards of data protection and operational integrity, validated by rigorous ISO certifications.