Senior Forward Deployed Engineer

Key Responsibilities

• Own the most complex, high-visibility customer deployments end to end, from scoping and solution design through integration, go-live, and measurable business impact, often across multiple accounts in parallel.
• Architect and build the agent solution: design conversation flows, configure tools and guardrails, and integrate with the client's systems for each use case.
• Own prompt engineering for Voice and In-App AI Agents: write, iterate, and systematically optimise production prompts and conversation design, including multilingual and edge-case handling, driven by evaluation frameworks.
• Lead technical integration with customer systems via APIs, SDKs, and telephony, and own reliability, latency, and quality in production.
• Be the primary technical owner and trusted advisor for enterprise BFSI stakeholders, running solutioning sessions, demos, and workshops.
• Define prompting standards, deployment playbooks, and best practices, and review other engineers' work to raise the delivery bar.
• Partner with product and engineering to turn recurring field learnings into platform capabilities, and influence the roadmap.
• Mentor mid-level and junior Forward Deployed Engineers.
• May occasionally travel to or work from client sites to support deployments, represent RevRag AI on-site with the customer, and help ensure smooth operations.

Experience

• 4-5+ years building and shipping production software, with meaningful time in customer-facing, forward-deployed, or solutions engineering roles.
• Proven track record of independently owning and delivering complex technical projects to production and to business outcomes.
• Hands-on experience building with LLMs and GenAI in production (agents, RAG, tool calling, evaluations).
• Experience working with enterprise customers, ideally in BFSI, fintech, or another regulated domain.

Technical Skills

• Strong Python and software engineering fundamentals: clean, maintainable, well-tested code.
• Strong prompt engineering and conversation design for LLM agents: system prompts, tool use, structured outputs, guardrails, and evaluation-driven iteration.
• Deep understanding of LLM application development and LLMOps.
• Strong grasp of APIs, webhooks, SDK integration, asynchronous processing, and backend architecture.
• Experience on cloud platforms (AWS preferred), with comfort debugging latency, reliability, and production observability.
• Excellent communication, able to lead customer conversations, demos, and technical workshops with senior stakeholders.

What We're Looking For

You're a great fit if you:

• Have independently taken complex systems from ambiguity to production and owned the outcome.
• Are as comfortable writing and debugging prompts and agent logic as integrating backend systems.
• Set a high bar for quality and can raise it for others.
• Communicate with credibility in front of senior enterprise stakeholders.
• Thrive where there's no playbook, and create the playbook others follow.
• Care deeply about customer success and business impact.

Success in This Role

You'll be successful if you:

• Take flagship BFSI deployments live faster and with higher quality, driving measurable accuracy, latency, and conversion gains.
• Become the trusted technical partner for key accounts.
• Define the prompting and deployment standards the Forward Deployed Engineering team runs on.
• Turn field learnings into platform improvements.
• Level up the team through mentorship and reviews.

Bonus Points

Experience with any of the following will be highly valued:

• Production Voice AI systems
• LiveKit Agents
• Pipecat
• WebRTC
• Telephony integrations
• Building and scaling agent evaluation frameworks
• Fine-tuning using LoRA or QLoRA
• Indian language and multilingual conversational systems
• BFSI, fintech, or insurtech domain experience
• Leading customer deployments or mentoring engineers