AI Engineer | GENAI | GCP

Infinityquest It Services; Hyderabad, Pune District; Hybrid; INR 4,000,000 - 6,500,000; Full time

Job summary

Infinityquest It Services in Hyderabad is seeking an AI Engineer to design and build production-grade GenAI and ML services on GCP. You’ll own core platform components for hybrid RAG, vector + graph data stores, multi-agent orchestration, and secure tool connectivity (MCP-style). This is a purely technical role with strong ownership from design through running.

The role requires 8–10 years of backend or ML production experience, Python proficiency, and demonstrated GCP deployment expertise.

Qualifications

• 8–10 years building backend systems and/or ML engineering in production.
• Strong Python and backend fundamentals (async, concurrency, profiling).
• Experience deploying on GCP (Cloud Run/GKE), CI/CD, Terraform/IaC, Docker.

Responsibilities

• Build backend GenAI/ML services (GCP-first).
• Design scalable API-first services for LLM applications.
• Develop hybrid RAG pipelines with dense + sparse retrieval and grounding.
• Implement vector/graph DB-powered retrieval and multi-agent orchestration.

Skills

Backend systems

Python

GCP

LLM integration

Vector databases

Graph databases

MCP-style tools

ADK-style orchestration

Security mindset

Distributed systems

Tools

GCP (Cloud Run/GKE)

Terraform/IaC

Docker

CI/CD

Kubernetes

Job description

Role summary

We're hiring an AI Engineer to design and build production-grade GenAI and ML services on GCP. You’ll own core platform components for hybrid RAG, vector + graph data stores, multi-agent orchestration, and secure tool connectivity (including MCP-style patterns). This is a purely technical role with strong ownership from design through running.

Key responsibilities

Build backend GenAI/ML services (GCP-first)

• Design and implement scalable API-first services for LLM applications (chat/search/assistant capabilities).
• Build low-latency, high-throughput systems with robust caching, batching, retries, idempotency, and fallbacks.
• Integrate with GCP services (e.g., Cloud Run/GKE, Pub/Sub, Cloud Storage, Secret Manager, Cloud Logging/Monitoring).

Multi-agent orchestration (ADK-style frameworks)

• Implement agent orchestration patterns: planner‑executor, tool‑routing, specialist agents, critic/reviewer loops.
• Build state management, memory, and workflow execution with clear traceability and deterministic behavior where needed.
• Create reusable agent/tool SDK components for other engineering teams.

Hybrid RAG pipeline (dense + sparse)

• Build a hybrid retrieval layer (embeddings + keyword/BM25), reranking, metadata filters, query rewriting, and context compression.
• Implement ingestion pipelines: chunking strategies, deduplication, metadata enrichment, and incremental re‑indexing.
• Ensure response grounding with citations, provenance, and strict access controls.

Vector DB + Graph DB platform components

• Own vector indexing strategy, tenant isolation, lifecycle/retention policies, and performance tuning.
• Build graph-backed retrieval (GraphRAG / relationship-aware search) using entity linking and multi‑hop traversal.
• Design data models and services that combine vector similarity + graph context for better precision/recall.

MCP-style tool connectivity & enterprise integration

• Implement secure, standardised tool connectors (MCP-style) to internal APIs/data sources.
• Enforce authentication/authorisation, rate limits, audit logs, and policy checks per tool invocation.
• Provide a registry/catalogue of tools with versioned schemas and compatibility guarantees.

LLMOps/MLOps: reliability, evaluation, observability

• Build automated evaluation harnesses (golden sets, regression tests, red‑teaming, retrieval metrics).
• Implement production observability: tracing across agent steps, prompt/version tracking, cost and latency dashboards.
• Harden services with SLOs, incident runbooks, and safe rollout patterns (canary/blue green).

Responsible AI & secure engineering

• Implement mechanism against prompt injection, data exfiltration, and unsafe tool usage.
• Apply privacy-by-design: PII handling, data minimization, encryption, and auditability.
• Produce clear design docs (HLD/LLD), run technical reviews, and own operational readiness.

Required experience & skills

• 8–10 years building backend systems (microservices, APIs, distributed systems) and/or ML engineering in production.
• Strong Python (preferred for LLM/RAG) and solid backend engineering fundamentals (async, concurrency, profiling).
• Experience deploying on GCP (Cloud Run or GKE), CI/CD, Terraform/IaC, containerization (Docker).
• Hands‑on with LLM integration: embeddings, tool/function calling, structured outputs, prompt/version management.
• Proven delivery of RAG systems, ideally hybrid (dense + sparse) with reranking.
• Experience with vector databases (indexing, performance tuning, multi‑tenancy) and embedding pipelines.
• Experience with graph databases and modelling relationships for retrieval/reasoning use‑cases.
• Experience implementing agentic/multi‑agent workflows using an orchestration framework (ADK‑style or equivalent).
• Strong security mindset: secrets management, IAM, auditing, least privilege, threat modelling.
• Role & responsibilities