AI Engineer

What You Will Work On

● Platformized agentic workflows: Design and build reusable agent harnesses and orchestration services that other teams can plug into, rather than one-off bots.

● Framework evaluation and standardization: Evaluate, integrate, and standardize agent and orchestration frameworks (e.g., LangGraph, Amazon Bedrock Agent Framework/AgentCore) as core building blocks for our AI-native platform.

● Company-wide knowledge graph: Build ingestion pipelines, storage models, and APIs that expose LLM-ready context as a shared platform capability.

● Internal developer platform: Evolve our internal developer platform (Minerva/Vulcan/Veho Build) into the primary way to discover, consume, and safely extend internal APIs, with first-class AI/agent primitives.

● Security and guardrails: Implement cross-cutting policies (authZ, rate limits, capability scopes, audit trails) to ensure AI-powered features are safe by default.

● GitHub-native delivery: Build services that standardize how code, agents, and workflows move from branch to production via PRs, checks, and automated review.

● MCP server ecosystem: Operate a fleet of domain-specific MCP servers as platform components with clear SLAs, observability, and lifecycle management. Responsibilities

● Design, build, and operate scalable, multi-tenant platform services used by product, operations, and engineering teams.

● Develop and evolve APIs and systems across edge runtimes and cloud environments.

● Architect distributed systems spanning edge runtimes, cloud providers, and internal platforms.

● Embed AI and LLM-powered capabilities into platform surfaces (e.g., Vulcan, CI/CD, Slack), enabling safe agent workflows and tool use.

● Define standards, best practices, and reference implementations for building AI-native features at Veho.

What We’re Looking For

● 5+ years of software engineering experience with a focus on backend or platform systems.

● Strong fundamentals in APIs, distributed systems, and security for multi-tenant environments.

● Hands-on experience with LLMs, agent frameworks, or AI tooling (e.g., LangGraph, Amazon Bedrock Agent Framework/AgentCore, OpenAI, Anthropic) and a desire to treat them as platform primitives, not just product features.

● Experience building or contributing to internal platforms, API gateways, or developer tooling (e.g., GitHub-based workflows, CI/CD).

● Familiarity with GraphQL, service-to-service communication patterns, and observability for complex systems.

● Curiosity about the rapidly evolving AI ecosystem and a bias toward pragmatic infrastructure that teams readily adopt Nice to Have

● Experience with MCP or similar multi-tool/agent orchestration patterns in production.

● Background in platform security (fine-grained authorization, rate limiting, isolation boundaries).

● Prior work with AWS or GCP AI/agent services as part of a broader platform or developer experience initiative.

● Experience building internal Slack apps or workflow automation that integrate with platform services.

Pay: ₹1,500,000.00 - ₹2,500,000.00 per year

Benefits:

Food provided

Health insurance

Paid sick time

Paid time off

Provident Fund

Work Location: In person