Principal Forward Deployed Engineer

Systems Limited; India; On-site; INR 400,000 - 800,000; Full time

Job summary

Systems Limited is seeking a senior GenAI/agentic delivery lead to architect and ship production-grade AI solutions for enterprise clients in India.

You will own end-to-end delivery from PoC to production go-live, collaborating with client teams, integrating with existing systems, and guiding a delivery pod to ensure on-time, on-scope outcomes.

Strong technical leadership, hands-on GenAI/LLM experience, and comfort with on-site client interactions are required to succeed.

Qualifications

• 10–15+ yrs shipping production software with GenAI/LLM/build experience
• Full-stack GenAI app layer: orchestration, retrieval, integration, deployment
• Strong client-facing communication and on-site delivery experience

Responsibilities

• Own end-to-end build of GenAI/agentic solution from architecture to implementation
• Integrate into client live environment: auth, data access, legacy interfaces
• Adapt builds on-site based on real usage edge cases
• Debug and resolve production issues in client infrastructure
• Set up monitoring and handoff docs for client team
• Serve as primary technical contact during delivery
• Head the delivery pod for GenAI engagements when needed
• Support presales as pursuits surge
• Feed learnings back into estimation patterns
• Manage client expectations under changing scope or timelines

Skills

GenAI/LLM engineering

Full-stack development

Cloud deployment

Client facing

Production debugging

On-site delivery

Tools

LangChain

LlamaIndex

Azure AI Foundry

AWS Bedrock

Job description

Build and ship the GenAI/agentic solution end-to-end — from PoC through production go-live.

KEY RESPONSIBILITIES

• Own end-to-end build of the GenAI/agentic solution once scoped — architecture through implementation
• Integrate the solution into the client's live environment — auth, data access, existing systems, legacy interfaces
• Adapt the build on-site as real usage surfaces edge cases the original design didn't anticipate
• Debug and resolve production issues directly within the client's infrastructure
• Set up monitoring and handoff documentation for the client's own team
• Serve as the primary technical point of contact for the client during delivery
• Head the delivery pod for GenAI/agentic engagements when appropriate
• Flex into presales support when pursuit volume outpaces Hub capacity
• Feed build learnings back into the practice's estimation and pattern library
• Manage client expectations under shifting scope or timeline pressure

REQUIREMENTS & SKILLS

• 10–15+ yrs shipping production software, with hands-on GenAI/LLM/agentic build experience
• Full-stack range across the GenAI application layer — orchestration, retrieval, integration, deployment
• Comfortable debugging across the stack: infra, application code, model behavior
• Experience integrating with enterprise systems (SSO, legacy APIs, data governance constraints)
• Working knowledge of major agentic/GenAI platforms likely in the client's environment — Microsoft Azure AI Foundry, AWS Bedrock/Strands Agents, and Google Vertex AI; comfortable with open‑source alternatives (LangChain, LlamaIndex) as a good‑to‑have when the client has no platform preference
• Comfortable being the senior technical presence in the room with a client's engineering team
• Strong client‑facing communication — explains technical tradeoffs under time pressure
• Track record of taking ambiguous, partially specified designs to a working production system
• Resilient under the pressure of on‑site, client‑facing delivery with visible deadlines
• Prior forward‑deployed, startup, or embedded‑consulting experience is a strong plus