Agents & Enterprise Autonomy
About the Role
About the company:devx labs is an AI consulting firm that ships code. We help enterprises in India, Southeast Asia and the US design, build and run AI systems that move a business metric. Our clients work in retail, telecom, BFSI, the public sector, manufacturing, media and hospitality.We organise our capabilities into five practices, each owning one layer of a client's AI stack: Platform Engineering, Data & Decision Intelligence, Agents & Enterprise Autonomy, AI-Native Experiences, and AI Assurance & Governance.We partner with OEMs and AI labs to bring the most complex problems in enterprise AI to devx.
About the Role:
Agents & Enterprise Autonomy owns what AI does. We design agents that complete real work inside enterprise workflows, and grant them autonomy one action class at a time as their reliability is proven.The practice runs two tracks:
- Platform agents on low-code products such as Gemini Enterprise, for knowledge work and departmental workflows, with activation and adoption programmes alongside.
- Custom agents built in code, typically on ADK, for core workflows that write to systems of record.
Across both, it covers single agents and multi-agent systems, tools and protocols, memory and context, durable execution, human-in-the-loop design and the autonomy policy for every action.The surface users see belongs to AI-Native Experiences, and the eval suite and guardrail policy to AI Assurance & Governance. You will work closely with both, and with Data & Decision Intelligence on the data your agents use.
Responsibilities
Shape and win the work
- Find the work worth automating with the client, and capture the baseline before
- anything is built.
- Run technical discovery with client CTOs and architects: systems of record, APIs, identity, and how each write can be undone.
- Design agent architectures and autonomy tiers, and write the technical sections of proposals and SOWs.
- Shape prototypes on real cases that show the agent doing the work.
Hand over and advise
- Hand the solution to the delivery team with a clear agent design, autonomy tiers and decision log, on the platform or custom track.
- Advise the delivery team on tools, context, memory and the deterministic spine when they need it.
- Set the bar, with AI Assurance & Governance, for promoting actions to autonomy only on measured pass rates.
Drive go-to-market with partners
- Co-sell with OEM partner teams, build joint sales plays, and help clients qualify for partner funding.
Build the practice
- Shape reusable assets with the delivery team: agent templates, connector patterns, and domain harnesses for retail and frontline work.
- Write points of view, speak at events, and help others in the practice grow.
Scope scales with seniority, from solutioning parts of a deal to owning client agent programmes, partner relationships and the practice roadmap.
Requirements
Agent frameworks and platforms
- Google ADK in depth, plus LangGraph, Microsoft Agent Framework, OpenAI Agents SDK or Claude Agent SDK
- Gemini Enterprise, including Agent Designer, connectors and agent governance; Gemini Enterprise Agent Platform for runtime, Memory Bank and sessions
- Working knowledge of AWS Bedrock AgentCore and Microsoft Copilot Studio
Protocols and integration
- MCP: server and tool design, security, and OAuth-based authorisation
- A2A for agent-to-agent work, and Agent Skills for packaged know-how
- Integration with systems of record such as SAP, Salesforce, ServiceNow and telecom OSS/BSS, through APIs and events
Agent engineering
- Orchestrator-worker and multi-agent patterns, and knowing when a single agent is enough
- Context engineering: small tool sets, just-in-time retrieval, compaction and sub-agents
- Memory, durable execution with tools such as Temporal, retries and idempotent writes
- Human-in-the-loop design, and autonomy tiers set by reversibility and blast radius
Models and evaluation
- Choosing and switching between Gemini, Claude, GPT and open models on cost, latency and quality
- Agent evals built with AI Assurance & Governance: trajectory checks, pass rates
- across repeated runs, real-case test sets
- Retrieval over enterprise content: chunking, embeddings, re-ranking and grounding
Good to have: Google Cloud Professional Machine Learning Engineer or Cloud Architect certification; domain depth in one of the industries we serve.
Benefits & Perks
- AI tool credits and freedom to experiment with modern approaches.
- Performance-based appraisal at 6 months + annual appraisal cycle.
- Competitive pay with a structured CTC breakup.
- Work with clients across industries and domains.
- Hybrid model with work-from-home support and flexible working hours.
- No-cap leave policy — take time off responsibly, no fixed limits.
- Health insurance with spouse and kids coverage included.
- Yearly outings, and an open environment for innovation.
Reimagining customer experience, from first principles.
devx labs is an AI-native consulting firm that reimagines business operations around AI capabilities to deliver customer experience transformation for forward-thinking brands. We combine the unbiased perspective of young, AI-native talent with the seasoned judgment of experienced practitioners — solving for outcomes, not shipping deliverables for their own sake.
Reimagining every customer touchpoint across the entire journey.
Optimizing downstream operations to enhance customer experience delivery.
The foundation that makes AI-native experiences possible.