AI Platform Engineer Onsite - Gurugram

Uplers Solutions Private Limited.; Gurugram District; On-site; INR 2,250,000 - 2,750,000; Full time

Job summary

Uplers Solutions Private Limited in Gurugram is hiring an AI Platform Engineer to build and own the shared runtime our AI agents run on, and the evals that keep it honest.

The role requires delivering an agent runtime and a robust gateway to Anthropic, OpenAI and others, with fast policy checks and audit logging.

Office in Gurugram, Monday to Friday, reports to the engineering lead, and focuses on safety, cost control, observability, and scalable design.

Qualifications

• 3–5 years total experience with 2+ years backend engineering.
• Production experience with LLMs or agent systems.
• Experience building reusable platforms or SDKs.

Responsibilities

• Own agent runtime orchestration platform for prompts routing and tool execution.
• Build eval harness, datasets, calibrated LLM-as-judge and CI regression gates.
• Manage cost, latency and vector search integrated into the agents.
• Ensure safety, brand isolation, and audit logging for assets.
• Provide observability with tracing to diagnose outputs.

Skills

content provenance

eval tooling

Policy engines

LLM/agent system

Python

FastAPI

Tools

Docker

AWS

GCP

Azure

Job description

Job Description:

Experience

3.00 + years

Salary

INR 2500000.00 / year (based on experience)

Expected Notice Period

7 Days

Shift

(GMT+05:30) Asia/Kolkata (IST)

Opportunity Type

Office ()

Placement Type

Full Time Permanent position(Payroll and Compliance to be managed by: N/A)

*Note: This is a requirement for one of Uplers' client - N/A

What do you need for this opportunity?

Must have skills required:

content provenance, eval tooling, Policy engines, LLM or agent system, Docker, AWS, GCP, Azure, Python, FastAPI

About The Founders

We are second-time entrepreneurs and operators behind Momspresso, acquired by Honasa/Mamaearth in 2023, along with leadership experience across companies like Unilever, PepsiCo, Aviva, and WinZO.

We have worked with 300+ brands across FMCG, BFSI, DTC, healthcare, retail, and other consumer categories.

The Role

We're hiring an AI Platform Engineer to build and own the shared runtime our AI agents run on, and the evals that keep it honest.

We run AI agents on behalf of brands. Those agents need one gateway to the models, one place prompts get routed, and one gate that checks what is allowed before anything ships. And they need proof they work, because a brand cannot take our word for it.

Reports to the engineering lead. Individual contributor. Office in Gurugram, Monday to Friday.

The Hard Problems

• Build one agent runtime that new use cases plug into, without forking the code.
• Build evals strong enough to block a bad release, not just report on it.
• Run a policy gate on every generated asset, fast enough to sit in the request path.
• Keep many brands on one platform, where Brand A''s memory never reaches Brand B''s output.

Core Responsibilities

• Agent runtime and LLM gateway: Own one reusable platform for agent orchestration, tool execution and prompt routing, with a single path to Anthropic, OpenAI and others (caching, dedup, fallback, retries).
• Evals and release gates: Build the offline and online eval harness, golden datasets, calibrated LLM-as-judge and a CI regression gate that stops a prompt change that drops a score.
• Cost, retrieval and latency: Own inference spend per unit of output, prompt caching, and vector search over brand history (pgvector or similar) wired into the agents.
• Safety and brand isolation: Own the sandboxed policy gate, disclosure metadata and audit log on every asset, prompt-injection defence, four autonomy tiers, a kill switch and one-step rollback.
• Observability and design: Trace every agent step with OpenTelemetry so a wrong output points to the step that caused it, and own high-level and low-level design.

What We''re Looking For

• 3–5 years of total experience, with 2+ years in backend engineering. Python, FastAPI in production.
• Shipped an LLM or agent system to production: not a demo, not a notebook.
• Built a platform others build on: SDK, shared service or internal framework with real users.
• Built an eval harness that blocked a bad release. Tell us about the release it blocked.
• Cost or latency work you can quantify. You cut a number and you know how.
• RAG in production. Embeddings, a vector store, chunking choices you can defend.
• Cloud and CI/CD. AWS or GCP, Docker, GitHub Actions or equivalent.
• Distributed systems basics. Caching, queues, idempotency, P99 latency.
• Written design docs. Led at least a small team or a large project end to end.
• Good to have: eval tooling (Braintrust, LangSmith, DeepEval, or your own), policy engines (OPA/Rego, sandboxes), content provenance (C2PA, watermarking, EU AI Act), ad tech or martech, and side projects with agents. We read them.

Why Join

We''re not just building software. We''re reshaping how brands understand and scale creativity with AI. You will build the platform every agent runs on, and the measurement that proves it works.

This is an early role in a company built from the ground up. What you build becomes the foundation others build on.